Dictation API: AssemblyAI cleaned text vs Sume STT word timings
AssemblyAI's Dictation API returns send-ready text. Sume STT returns a transcript with words[] timings and no cleanup flag, so you do the filler removal.
Models
The models behind Sume's video, image, speech, and music endpoints: ids, clip lengths, resolutions, aspect ratios, audio, references, and migration.
Start with: What AI models does Sume support? Every model id, by API surface
AssemblyAI text to speech: coming soon, and what Sume has today
AssemblyAI's product menu lists a Text-to-Speech API as coming soon. Sume TTS is available now: what a call takes, the 20000-character cap, and word timings.
Creatify Boreal talking clips vs Sume's still-plus-audio route
Creatify says Boreal's gains are smallest on single-person talking clips. Sume makes every speaking shot from an accepted still plus TTS audio via Fabric.
Deepgram nova-3-pharma vs Sume STT: drug-name transcripts
Deepgram added nova-3-pharma for English drug names. Sume STT has one public model, sume/stt-1.0, so check each drug name against word timings.
ElevenLabs character limits by model vs Sume TTS 20,000
ElevenLabs lists 5,000 characters for v3, 10,000 for v4 and 40,000 for Flash v2.5. Sume TTS 1.0 takes up to 20,000 characters in one request.
ElevenLabs speech to speech API: what Sume offers instead
ElevenLabs lists speech-to-speech voice changer models. Sume has no voice-to-voice endpoint: transcribe with STT, edit the text, then run TTS.
FLUX.2 flex steps and guidance: BFL has them, Sume does not
BFL lists adjustable steps and guidance only for FLUX.2 flex ($0.06/MP). Sume lists flux.2-flex but rejects unlisted parameters with 400.
FLUX.2 max grounding search: what it is, what Sume lists
Only FLUX.2 [max] does web-grounded generation at BFL. Sume lists flux.2-pro and flux.2-flex, so grounding is not available there.
GPT Image aspect ratios for a Pinterest pin (2:3) and Instagram (4:5)
Sume lists 17 aspect ratios, including 2:3 for a Pinterest pin and 4:5 for an Instagram portrait. A model only accepts the ratios its catalog row lists.
HappyHorse 1.0 API: what Runway lists and how to check Sume's models
Runway lists HappyHorse 1.0 at 3-15 seconds, 720p and 1080p. Sume's video docs name no such id, so read /v1/videos/models before you plan around it.
HeyGen cinematic avatar API: 3 looks per shot vs Sume's one
HeyGen cinematic_avatar takes a prompt and 1-3 avatar looks with no script. Sume Avatar Video resolves one avatar per final video from a script.
Kling 4.0 21:9 ultrawide: check Sume's aspect ratios
Kling 4.0 supports 21:9 output. Sume documents 21:9 as a ratio, but each model lists its own supported_aspect_ratios, so read them before sending.
Kling 4.0 Flash early access: how to tell what Sume lists
Kling 4.0 Flash opened to a limited group on Sept 28 with full launch in October. On Sume, a model is callable when the live catalog lists it.
Kling 4.0 stereo audio vs Sume's generate_audio flag
Kling 4.0 moves to two-channel stereo audio. Sume exposes generate_audio and per-model audio capability; check the catalog for what each model reports.
Ray 3.2 API aspect ratios and resolutions, and Sume's lists
Luma lists six Ray 3.2 aspect ratios (9:16 to 21:9) at 540p, 720p and 1080p. Sume reports ratios per model in supported_aspect_ratios and rejects size.
Seedance 2.0 4K price: Luma 261 credits/sec, Runway 150, Sume 1080p
Luma lists Seedance 2.0 at 4K for 261 credits per second; Runway's docs list 150. Sume's docs list seedance-2 at 480p, 720p and 1080p, with no 4K entry.
Nano Banana multiple images at once: n range vs Gemini's count
Google says Gemini won't always return the exact image count you ask for in a prompt. On Sume, set n, and read each model's n range from the catalog.
Nano Banana video to image: poster from a video via Sume stills
Google's Gemini API takes a video as context for a thumbnail or poster. Sume's images API takes image references only, so grab a still frame first.
Runway video_to_hdr alpha and ProRes 4444: what Sume returns
Runway's /v1/video_to_hdr now keeps source alpha and delivers ProRes 4444. Sume docs describe no alpha or ProRes output; a completed video job is a download.
Speechmatics Linden for voice agents vs Sume batch STT jobs
Speechmatics announced Linden for voice agents. Sume STT is a bounded batch job with a webhook, not a live stream, so live agents need streaming.
Synthesia Interactive Avatar API vs Sume rendered avatar clips
Synthesia headlines a live Interactive Avatar API. Sume avatar video is script-driven and rendered as a job: submit, poll, then fetch the clip.
Adobe Firefly Image 5 API: native 4 MP vs Sume resolution tiers
Firefly's Image5 model is described as native 4 MP with Instruct Edit. Sume does not list a Firefly model; it uses 512, 1K, 2K and 4K tiers.
Fish Audio Drama 3 single-word fix vs Sume sentence segments
Fish Audio says Drama 3 preview can fix a single word. Sume has no word-level repair: regenerate a sentence and join takes with Timeline audio concat.
Flux TTS expressivity -2 to 2 vs Sume's emotion guide
Deepgram's Flux TTS expressivity runs -2 to 2 (0 nominal). Sume TTS has no such dial: generation_config takes volume, speed and a free-text emotion guide.
Gemini 3.1 flash image preview shutdown: Sume model ids
Google lists gemini-3.1-flash-image-preview and gemini-3-pro-image-preview for June 25, 2026 shutdown. Sume callers use catalog ids like google/nano-banana-2.
Hedra Character 3 aspect ratios vs Sume Avatar Video ratios
Hedra Character 3 lists seven aspect ratios including 9:21 and 21:9. Sume Avatar Video supports five: 1:1, 3:4, 9:16, 4:3 and 16:9, default 9:16.
Ideogram 8K output resolution API vs Sume 512 to 4K tiers
Ideogram 4.0 takes output_resolution 1k, 2k, 4k or 8k as a pixel budget. Sume's image route takes a normalized 512, 1K, 2K or 4K tier.
Ideogram Z-Image resolution rules vs Sume image_size
Ideogram Z-Image takes WIDTHxHEIGHT, sides in multiples of 16, area up to 1,048,576 px. Sume uses 512/1K/2K/4K tiers and GPT Image 2.5 custom pixels.
Edits Restyle with a prompt vs Sume video router edit mode
Edits Restyle changes a clip's look from a text prompt. In Sume, send video_url to the video router with a prompt to use gemini-omni-flash-1.1 edit mode.
Edits audio vibe filter vs a Sume music prompt (no duration field)
Edits lets you filter audio by vibe like chill or bossy. Sume music takes a text prompt instead, with no duration, seed or temperature parameter to pin.
Kling 4.0 10-bit HDR at 1080p and 4K: what later edits keep
Kling says 4.0 outputs 10-bit HDR at 1080p and 4K. Sume's exact video_trim re-encodes to yuv420p; keyframe trims stream-copy. Verify before you grade.
Kling 4.0 five reference videos vs Sume's 1 to 3 video URLs
Kling 4.0 takes up to 5 reference videos, 30 seconds combined. Sume lists 1-3 reference_video_urls on the legacy shape and varies per model.
Midjourney edit model image references: 4 vs Sume's ranges
Midjourney's V8.2 edit model takes up to 4 image references. On Sume the ceiling is per model: GPT Image 2.5 takes up to 16. Read the descriptor first.
minimax/hailuo-3 on OpenRouter vs Sume minimax-h3 id
OpenRouter names the model minimax/hailuo-3. Sume uses bare catalog ids, so the matching id is minimax-h3, native 480p/768p, with 2K and 4K as priced upscales.
Qwen-Audio-3.0-TTS languages: 16, and Sume's language field
Qwen-Audio-3.0-TTS lists 16 languages. On Sume TTS you set the language field to a BCP-47 or ISO-639 code for every non-English transcript.
Seedance 2.5 480p: ratio 864:496 gives 854x480, Sume uses resolution
On Runway, Seedance 2.5 ratios 864:496 and 496:864 return 854x480 and 480x854. On Sume you ask for 480p with resolution plus aspect_ratio, never pixels.
Seedream 5.0 Flash: which Seedream 5 id Sume's catalog lists
Higgsfield added Seedream 5.0 Flash on Sep 23, 2026. Sume's image catalog lists seedream-5-lite and no Flash id. Check GET /v1/images/models before calling.
Vidu Q2 Pro Fast image-to-video 1080p vs Sume first frame
QwenCloud lists vidu/viduq2-pro-fast_img2video at 720P and 1080P. Sume has no Vidu id; send image_url as the first frame to a 1080p model.
Vidu Q3 ad reference-to-video vs Sume reference images
QwenCloud lists a Vidu Q3 ad reference-to-video model. Vidu is not in Sume's video ids; reference images work on models that list them.
Vidu Q3 drama character consistency vs Sume reference images
QwenCloud lists Vidu Q3 drama for character consistency. Vidu is not in Sume's ids; on Sume, references guide a clip, and frame_images win if both are sent.
Wan 3.0 Prime vs Wan 3.0: one wan-3.0 id on Sume
QwenCloud and Runway list Wan 3.0 and a Prime variant. Sume's catalog lists one id, wan-3.0, with 2-30 s clips. Check the catalog for limits.
Wan 3.0 is public after invite-only: check Sume's wan-3.0 id
QwenCloud says Wan 3.0 went from invite-only on August 6 to public. On Sume, wan-3.0 is a catalog id; check the live catalog for limits.
Nova Reel EOL September 30, 2026: moving video jobs to Sume
Bedrock lists Nova Reel as Legacy with an EOL date of September 30, 2026. Remap StartAsyncInvoke to a Sume video job and read results from media URLs.
Creatify Aurora 2.0 max audio length: 59.7 s, and how to split
Creatify Aurora 2.0 takes up to 59.7 s of audio; Aurora v1 takes 5 minutes. Sume Avatar Video accepts 4-60 s per job, so split longer scripts across jobs.
D-ID V4 expressives sentiment_id vs Sume's emotion string
D-ID picks a delivery with a sentiment_id preset; Sume TTS takes a free-text emotion string plus a 0.6-1.5 speed multiplier. How each one is set.
FLUX 1.1 Ultra raw mode and 4MP: what Sume image size accepts
Raw mode and 4MP belong to BFL's FLUX1.1 [pro] Ultra endpoint. Sume lists FLUX.2 ids and sizes images with aspect_ratio, resolution tiers and image_size.
FLUX.1 Kontext pro vs FLUX.2 for edits: what to use on Sume
BFL calls FLUX.1 Kontext [pro] previous-generation and recommends FLUX.2 for edits with up to 10 references. On Sume, use flux.2-pro with input_references.
FLUX.2 klein 4B Apache 2.0 vs 9B non-commercial, and Sume ids
BFL releases klein 4B weights under Apache 2.0 and 9B under the FLUX Non-Commercial License. Sume's image catalog lists flux.2-pro and flux.2-flex, not klein.
FLUX.2 native-language prompts: Japanese or Korean vs English
BFL says native-language FLUX.2 prompts often look more culturally authentic. Send both versions to a Sume FLUX.2 id with n and compare the results.
Veo 3.1 Lite preview shuts down Oct 22: Omni Flash on Sume
Google lists veo-3.1-lite-generate-preview shutting down October 22, 2026 with gemini-omni-1.1-flash as replacement. Sume id: gemini-omni-flash-1.1.
Grok Imagine Video 1.5 text-to-video at 1080p: xAI vs Sume
xAI lists native 1080p text-to-video for grok-imagine-video-1.5. Sume's row is image-to-video only at 480p and 720p. How the two differ and what to send.
HappyHorse 1.1 API ids: 480P to 1080P, 3 to 15 seconds
Alibaba lists happyhorse-1.1-t2v, -i2v and -r2v at 480P, 720P or 1080P for 3 to 15 seconds. Sume's catalog docs name HappyHorse 1.1 as not in the v1 catalog.
Ideogram 4 custom_model_uri vs Sume catalog ids and sume/auto
Ideogram's custom-model endpoint picks a private model by custom_model_uri. Sume has no such field: you choose a catalog id or sume/auto. What to send instead.
OpenAI organization verification for GPT Image 2.5 and Sume ids
OpenAI says you may need API Organization Verification before using GPT Image models. Sume lists the same two models as openai/gpt-image-2.5 and -sunburst.
Recraft V4 Styles: 10 references, and the Sume Recraft id
Recraft V4 Styles takes one to 10 reference images in Precise or Flexible mode. Sume lists recraft/recraft-v4 as text-to-image only and rejects references.
Suno v6 change one lyric: what Sume Music does instead
Suno v6 can swap one lyric or line and keep the rest. Sume Music is brief-driven and documents no lyric editing, so you edit the brief and generate a new track.
Sync react-1 model_mode and emotion vs Sume TTS emotion and speed
Sync react-1 edits an existing video with model_mode lips, face or head plus an emotion prompt. On Sume, emotion and speed are set in the TTS audio request.
wan2.2-animate-move vs animate-mix, and Sume's motion transfer
animate-move drives a still character with a reference video; animate-mix swaps a character into a video. Sume's Genjutsu row covers the move-style case.
wan2.7-videoedit camera replication vs Sume's video_url edit
Alibaba names wan2.7-videoedit for effect and camera-movement replication. On Sume, video edit is the video_url field on the Gemini Omni Flash 1.1 id.
YouTube fhd, qhd, uhd thumbnails in the API: a 3840 AI image
YouTube's API notes fhd, qhd and uhd thumbnail keys for some videos. Sume's ChatGPT Image 2.5 image_size accepts a 3840 edge, enough for a 4K image.
Cartesia Sonic 2 and Turbo stop October 20: Sume model ids
Cartesia retires sonic-2 and sonic-turbo on October 20, 2026. Sume's TTS Router lists sonic-3.6, 3.5, 3, latest and preview; here is what to send instead.
ElevenLabs STT edit instructions vs Sume transcribe: what Sume returns
ElevenLabs added transcript-editing instructions up to 2,000 characters to its speech to text. Sume's transcribe endpoint returns a plain transcript.
ElevenLabs dialogue continuity vs Sume TTS segments: what differs
ElevenLabs Text to Dialogue links takes with previous_text and request ids. Sume TTS has no such fields; it returns gapless sentence segments instead.
Lyria 3 Clip vs Lyria 3.5: which one runs on Sume?
Google lists Lyria 3 Clip as a 30-second model and Lyria 3.5 as minutes long. Sume's Music Router routes lyria-3.5, lyria-3-pro or sume/music-auto.
Lyria 3.5 takes 131,072 tokens; Sume music prompts, 5,000 chars
Google lists a 131,072 token input limit for Lyria 3.5. Sume's music prompt field takes 1 to 5,000 characters. What fits and how to trim.
Lyria 3.5 takes up to 10 images; Sume music takes one image_url
Google's Lyria guide allows up to 10 images as input. Sume's music docs describe one optional public HTTPS image_url. What that changes.
Can I distribute AI music through TuneCore? Suno vs Sume tracks
Suno says tracks from its partner model can go out through Believe and TuneCore. That is a Suno feature. What it means if your tracks come from Sume.
Veo 3.1 only makes 16:9 and 9:16; which Sume video models add more
Google's Veo 3.1 supports 16:9 and 9:16. On Sume, Seedance, MiniMax and Wan add 4:3, 1:1 and 3:4, Kling adds 1:1, and Grok takes no ratio.
Veo 3.1 prompts cap at 1,024 tokens; Sume's Omni at 20,000 characters
Google caps a Veo 3.1 text prompt at 1,024 tokens. On Sume, gemini-omni-flash-1.1 documents a 20,000-character cap. Tokens and characters differ.
Which Sume video models accept an audio reference?
Seven Sume video models take reference audio: the four Seedance 2.x ids, Wan 3.0 and the two MiniMax H3 models. Kling, Grok and Gemini Omni Flash do not.
Which Sume video models accept a reference video?
Nine Sume video ids take a video input: the four Seedance 2.x ids, Wan 3.0, both MiniMax H3 models, Omni Flash and Genjutsu. Kling and Grok do not.
Anam Cara-4 anime and 3D avatar images vs Sume's photo input
Anam says Cara-4 animates anime and 3D character images. Sume's avatar API takes a prompt, profile or public HTTPS reference image and promises no style.
Anam Cara-4 Director Notes vs Sume scene prompts and silence
Anam Director Notes steer a live avatar with a style and an Expressivity control. Sume directs scenes with a prompt or photo, silence beats and a quality tier.
Anam Cara-4 portrait 768x1152 vs Sume 9:16 avatar at 720p
Anam Cara-4 renders natively at 768x1152 portrait. Sume's avatar video defaults to 9:16 at a fixed 720p, with plans estimated at 4-60 seconds.
AssemblyAI Universal-3.6 Pro 32 languages vs Sume STT language_code
AssemblyAI streaming defaults to Universal-3.6 Pro with 32 languages; 3.5 Pro has 19. Sume STT 1.0 takes one optional language_code hint and auto-detects.
Sonic 3.6 written disfluencies: pacing and Sume's emotion guide
Sonic 3.6 shifts pacing for written hesitations like uh. How to write a natural-sounding transcript, and what Sume's optional emotion guide adds.
Cartesia STT keyterms for brand names, and Sume STT without keyterms
Cartesia STT adds keyterm prompting for brand names and invented words. Sume STT has no keyterm field, so here is how to fix brand names after transcription.
Deepgram Nova-3 de-CH, Lithuanian, Portuguese: language_code on Sume
Deepgram improved Nova-3 for Swiss German, Lithuanian and Portuguese on September 24. What to send as language_code on Sume STT for regional variants.
FLUX 3 Action is a robot-control model, not an image model
FLUX 3 Action is an open-weight 7B world action model for robots. It predicts actions, not images, so it is no drop-in for the FLUX ids Sume serves.
FLUX 3 Image bounding boxes vs Sume masked edit: what each takes
FLUX 3 Image takes a JSON list of boxes at the end of the prompt. Sume's image edit takes a mask image: mask_image_url with image_urls. Differences, no overlap.
FLUX 3 Image 10 reference images vs Sume's 1-10 image_urls
FLUX 3 Image takes up to ten references named by prompt position. Sume's image edit takes one to ten public image_urls, with no FLUX 3 id in the docs.
FLUX 3 x mimic: one backbone for video, audio and robot actions
BFL says FLUX 3 is one model trained jointly on images, video and audio, and FLUX-mimic adds robot actions. What that does and does not tell a media API user.
FLUX 3 video continuation caps at 15 s: extending a clip on Sume
BFL cut FLUX 3 video continuation (v2v) to 15 seconds on Aug 17; other modes stay at 20. Sume has no continuation mode: chain a last frame instead.
FLUX 3 Video 4K uhd (3840x2176) and which Sume video models do 4K
FLUX 3 Video's uhd resolution is 3840 x 2176 at 16:9. On Sume, a 4K request goes to a model whose supported_resolutions lists it; here is what the docs say.
Gemini 3.8 Live Extended Thinking: the id, and Sume's audio ids
gemini-3.8-live-extended-thinking is a Live API audio-to-audio model id. Sume has no live audio route; its audio ids are sume/music-auto and TTS Router ids.
Grok Imagine 21:9 and 5:2 ratios vs Sume's Grok aspect list
xAI added 21:9 and 5:2 to Grok Imagine image on Aug 28. Sume's Grok list has 20:9 and 2:1 but neither of those two, so pick a listed ratio for banners.
Genjutsu Restyle's 20+ styles vs Sume motion transfer inputs
Higgsfield Genjutsu Restyle picks from 20+ styles in its app. Sume's motion transfer takes a source video plus 1 to 8 reference images, with no style list.
Kling 4.0 on-screen text vs Sume burned-in captions
Kling 4.0 renders on-screen text inside the video. Sume burns captions onto a finished clip; language is a speech-to-text hint, and cues add authored text.
Kling 4.0 video extension, forward or backward, done by hand on Sume
Kling 4.0 extends a video forward or backward in one workflow. On Sume you chain clips yourself: pull a frame, pass it as first_frame or last_frame.
Kling Avatar output length follows audio; Sume H3 Max is 5-14.8 s
On fal, Kling Avatar v2 Pro output duration matches the audio file. On Sume the audio sets length too, within route windows from 5 to 14.8 s up to 60 s.
Kling Avatar v2 Standard vs Pro: fal tiers vs Sume quality
fal prices Kling Avatar v2 Pro at $0.115/s and Standard at $0.0562/s. Sume Avatar Video has its own quality values: standard, plus and max.
MiniMax H3 Max reference audio needs an image or video on Sume
Krea says MiniMax H3 Max audio references cannot be sent alone; Sume's reference_audio_urls has the same rule. Limits for images and videos compared.
Wan 3.0 references or start/end frames, not both: two Sume calls
Krea says a Wan 3.0 job takes reference media or start/end frames, not both. Sume lists them as separate modes, so split the work into two requests.
LTX-2.5 Cinemagraph LoRA vs image-to-video on Sume
The LTX-2.5 Cinemagraph LoRA is an image-to-video adapter for selective motion. On Sume, start from first_frame and describe the motion in the prompt.
Luma layers API: 10 RGBA layers vs Sume's flat image result
Luma type layering splits one image into up to 10 ordered RGBA PNG layers. Sume returns flat images at data[].url; n counts images, not layers.
Luma Scenes Ray 3.2 or Seedance 2: pin a model or use auto
Luma says Ray 3.2 and Seedance 2 are not interchangeable. On Sume, pin a catalog model for a known clip length, or send sume/auto and let Sume pick.
Luma uni-1 API: image models, types, and what Sume lists
Luma's API has two image models, uni-1 and uni-1-max, each with image and image_edit types. Sume lists its own catalog; check the models endpoint.
MAI-Transcribe-2 languages (60) vs Sume STT language hint
Microsoft's MAI-Transcribe-2 preview covers 60 languages. Sume STT 1.0 takes one optional language_code hint and auto-detects when you omit it.
MAI-Transcribe-2 speaker diarization vs Sume STT: no speaker field
MAI-Transcribe-2 attributes each segment to a distinct speaker. Sume STT has no diarize field: provider knobs are fixed server-side and you get words[].
MiniMax-H3 Fun ControlNet Union 2.0: 8 conditions vs Sume references
MiniMax-H3-Fun-Controlnet-Union-2.0 adds Scribble, Layout and Gray to five older conditions. Sume's minimax-h3 ids take image, video and audio references.
MiniMax H3 license for an EU company: contact MiniMax first
MiniMax H3 license Section II invites people in the EU, UK, Korea and USA to contact MiniMax about a license. What it promises and omits.
MiniMax H3 license: EU, UK, Korea and US are Excluded Territories
The MiniMax H3 Community License defines the EU, UK, Republic of Korea and USA as Excluded Territories and says use there is not authorized. What it quotes.
Muse Voice Transcribe 25+ languages and code-switching vs Sume STT
Muse Voice Transcribe supports 25+ languages and code-switching in one conversation. For mixed-language audio on Sume STT, omit language_code or set one hint.
Muse Voice Transcribe keyword biasing vs Sume STT: no vocab field
Muse Voice Transcribe has keyword biasing for names and domain terms. Sume STT has no vocabulary field: its request takes a language hint and word timings.
Pika Camera Director vs a prompted video edit on Sume
Pika Camera Director reshoots a scene from new angles. On Sume, Omni Flash 1.1 edits a clip from a video_url and a prompt; there is no camera-angle parameter.
Invisible models in Pika vs Sume Auto echoing sume/auto
Pika hides model names unless you ask. Sume's model sume/auto also hides the family and echoes sume/auto; pin a catalog id when you need a known model.
Pika Soundtrack: video in, sound out. What Sume has instead
Pika Soundtrack scores a finished video. Sume's docs offer generate_audio at video creation and a Timeline soundtrack bed, but no video-to-sound endpoint.
30-second video with sound: Pika Video Studio vs Sume ids
Pika Video Studio makes up to 30 seconds with sound. On Sume, seedance-2.5 and wan-3.0 reach 30 seconds; every other catalog model stops at 15.
Pika Video Studio's 50 references vs Sume's per-model limits
Pika Video Studio attaches up to 50 references. Sume's caps are per model: 10 images and 3 short clips on Omni Flash, 1 to 8 images on Genjutsu.
Qwen-Image 2.1 ControlNet Union Fun in ComfyUI vs reference images
ComfyUI added Qwen-Image 2.1 ControlNet Union Fun for editing on 2026-09-29. Sume has no ControlNet input; it edits with reference images and masks.
Qwen Image 2.1 license: research only, commercial needs a request
Qwen-Image-2.1 ships under the Qwen Research License: non-commercial means research or evaluation only, and commercial use needs a separate license.
Runway Compositing Nodes vs Sume Timeline compose
Runway added compositing nodes to blend images and video in Workflows. Sume's Timeline compose puts one still and one video in one MP4: stack or overlay.
Synthesia Express-3 follows script sentiment; Sume's script controls
Synthesia Express-3 avatars follow script sentiment. Sume Avatar Video is steered by script text, silence beats, scene direction and quality tiers.
Tavus 50 new Phoenix-4.5 stock faces vs a Sume avatar handle
Tavus added 50 first-party Phoenix-4.5 stock faces, 28 of them Pro. On Sume you create your own avatar from a prompt, profile or image and reuse its handle.
VEED lipsync-v2 video + audio vs Sume still + audio lip sync
fal lists veed/lipsync-v2 as video plus audio in. Sume lip sync routes start from a still and an audio clip, so existing footage is not re-synced.
Wan-Animate-2 14B: Apache 2.0 weights vs Sume Motion Transfer
Wan-Animate-2 14B weights are Apache 2.0 and ship inference scripts. Sume's Motion Transfer takes one source video plus 1-8 reference images, 4-30 s.
Wan-Animate-2 Base vs Distillation weights: which to download
Wan-Animate-2 ships Base and Distillation checkpoints, each with its own YAML config. What the card says, and the hosted limits Sume lists for comparison.
WorldCrafter camera control: Base weights, adapter and LoRA
TencentARC WorldCrafter-Base ships transformer weights with a matching camera adapter and LoRA. On Sume, steer camera motion in the video prompt instead.
YuE2-3B license is CC-BY-NC-4.0: what that means vs Music Router
YuE2-3B is tagged cc-by-nc-4.0, a non-commercial license. Sume's Music Router routes sume/music-auto, lyria-3.5 and lyria-3-pro instead.
YuE2 48 kHz stereo on a 24GB GPU vs a hosted Sume music job
YuE2-3B needs a 24GB NVIDIA GPU with BF16 for 48 kHz stereo songs. A hosted Sume music job needs no GPU, only a prompt and an Idempotency-Key for retries.
Suno v6-wild: is there a less predictable setting on Sume?
Suno v6-wild is a paid model that is less predictable. Sume's music request has no seed, temperature or guidance field, so variety comes from the prompt.
Lyria 3.5 takes 10 images: Sume music takes one image_url
Google's Lyria 3.5 page lists up to 10 images alongside text. Sume's music request has a single optional image_url, so pick one accepted still per track.
GPT Image 2.5 cached input price: does Sume pass it on?
OpenAI lists cached input at $1.25 text and $2 image per million tokens for Sunburst. Sume's docs give estimates and reserved cost, not a cache discount.
Image quality default on Sume: low on Image 1.0, high on GPT 2.5
Image 1.0 defaults quality to low; ChatGPT Image 2.5 on POST /v1/images defaults to high when omitted. Values, and when to raise quality.
How many reference images? 10 on Image 1.0, 16 on GPT Image 2.5
Image 1.0 image_urls takes 1 to 10 public HTTPS URLs; ChatGPT Image 2.5 takes up to 16 references. Text-only models reject references.
gpt-image-2 or openai/gpt-image-2? Model ids on Sume's Image API
Sume accepts bare Image Router ids such as gpt-image-2 and nano-banana-2 as aliases for openai/gpt-image-2 style ids. The catalog lists org/slug ids.
DALL-E 3 API removed May 12, 2026: GPT Image ids on Sume
OpenAI removed dall-e-3 from its API on May 12, 2026 and points to gpt-image-2. On Sume, send openai/gpt-image-2 to POST /v1/images instead.
FLUX video edit API: 720p downscale, and video_url edits on Sume
BFL's edit-a-video endpoint downscales sources above 720p. Sume lists no FLUX video; its edit path is video_url with gemini-omni-flash-1.1 only.
gemini-2.5-flash-image shutdown on October 2, 2026
Google lists gemini-2.5-flash-image for shutdown on October 2, 2026. Sume lists Nano Banana 2 and Pro under google/ ids to move image requests to.
Gemini 3.5 Transcribe API limits: 1 hour vs Sume STT's 10 minutes
Gemini 3.5 Transcribe takes up to 1 hour per request, 30 minutes with diarization or word timestamps. Sume STT takes 600 seconds; split longer audio.
Gemini API speaker diarization: 8 speakers; Sume STT has no labels
Gemini 3.5 Transcribe diarizes up to 8 speakers, 3+ experimental, within 30 minutes per request. Sume STT returns word timings but no speaker labels.
Gemini Omni video editing: the EEA, UK and under-10-second rules
Google says editing or extending uploaded videos with Omni is unavailable in the EEA, Switzerland and the UK, and uploads must be under 10 seconds.
Gemini Omni extend video: Google's 40 s cap vs Sume's modes
Google's Gemini Omni can extend a video by 3-10 s up to 40 s. Sume's Omni row has no extend mode; here is what it offers instead.
Gemini TTS API: which engine Sume's TTS routes to
Gemini 3.8 TTS is not in Sume's TTS Router, which lists Cartesia Sonic ids only. What Sume's TTS takes for voice, engine and length, with a checklist.
Genjutsu Object Swap API: Sume serves Motion Transfer only
Higgsfield pairs Motion Transfer with Object Swap in Genjutsu. Sume's Genjutsu row serves Motion Transfer only; Object Swap is rejected by name.
grok-imagine-image-quality retires Nov 2: what about quality?
xAI retires grok-imagine-image-quality on November 2, 2026 and serves it as grok-imagine-image-2.0 at low quality. Sume's x-ai/grok-image takes no quality.
Grok Imagine video editing: 8.7 s on xAI, Omni edit on Sume
xAI caps Grok Imagine video edits at 8.7 seconds. Sume's Grok row has no video-to-video; edits go through gemini-omni-flash-1.1 with a video_url.
Grok Imagine video sound: xAI audio vs Sume's silent row
xAI's Grok Imagine video makes audio unless generate_audio is False. Sume's grok-imagine-video-1.5 row lists audio: false and rejects generate_audio.
Hy-Image-3.5-Preview API limits vs Sume's image limits
Tencent's Hy-Image-3.5-Preview takes 256 to 8192 px edges, up to 4096x4096 and 20 references. Sume lists no Hy Image model; its own limits are below.
Ideogram 4.5 Precise Edit API: mask and reference limits
Ideogram 4.5 Precise Edit takes 4 reference images, 3 when a mask is sent. Sume lists Ideogram V3, and mask_url there is only for ChatGPT Image 2.5.
Kling 2.1 API sunset: 410 Gone, and the kling-3 id on Sume
Krea retired Kling 1.0 through 2.1: endpoints return 410 Gone after Sep 15, 2026. Sume lists kling-3 in its video catalog; here is what to change.
MiniMax H3 Max Turbo API: what Sume lists today
Krea added MiniMax H3 Max Turbo on Sep 9. Sume's video catalog lists minimax-h3 and minimax-h3-max, not a Turbo id. What each listed id accepts.
MiniMax H3 Max Turbo price: fal's rates, and the id Sume lists
fal prices H3 Max Turbo separately from H3 Max. Sume's docs list only minimax-h3-max; how to check the catalog, and what that id bills for 5 seconds.
MiniMax music API closed to new users: the Sume Music Router route
MiniMax stopped offering its paid Music and Lyrics APIs to new users on Aug 20, 2026. Sume's Music Router, sume/music-auto, is open: one POST, flat price.
Nano Banana Pro aspect ratio: auto keeps the reference shape
Freepik's changelog says Nano Banana Pro accepts aspect_ratio auto to follow reference images; omitting it stays 1:1. On Sume, omitting is also not auto.
Recraft V4.1 Flash API: Sume lists V4, webp, text-only
Recraft V4.1 Flash is live in Recraft Studio and its API. Sume lists recraft/recraft-v4, not a Flash id: webp output, text-to-image only, no references.
Medical transcription API: what Sume STT does and doesn't
Sume has one speech-to-text route, sume/stt-1.0, with no medical model option. What it takes and returns, so you can decide for clinical audio.
Seedream 5.0 pro layer decomposition vs a Sume Seedream result
Seedream 5.0 pro can split one image into a base plus up to 16 PNG layers. Sume lists Seedream 5.0 Lite, and results are one Sume-hosted URL per image.
Suno v6 audio and video input vs Sume: text and one image
Suno v6 says you can create with text, audio, images and video. Sume's music request takes a text prompt and one optional image; audio and video are not inputs.
Wan 3.0 on Runway, or the wan-3.0 id as an API job on Sume
Runway's changelog lists Wan 3.0 in tool mode and workflows on paid plans. On Sume, wan-3.0 is a model id you call from code and poll as a job.
Vidu API: S2-Avatar live voice vs Sume avatar video jobs
Vidu S2-Avatar is a real-time voice model. Sume has no live session: you submit a script and a scene photo to an avatar job and fetch the finished video.
Vidu S2-Editing: live stream edits vs a Sume Omni clip edit
Vidu S2-Editing edits an incoming video stream in real time. Sume edits one finished clip with a prompt through Gemini Omni video_to_video, as an async job.
PixVerse API and R2 world model: Sume has no live session
PixVerse R2 is a persistent real-time world. Sume has no live session or action controls: video jobs return a clip you poll for or get by webhook.
Kling 4.0 30 seconds: Sume lists kling-3 at 4 to 15
Kling 4.0 announces 3 to 30 second generation. Sume lists kling-3 at 4 to 15 seconds; seedance-2.5 and wan-3.0 are the ids that reach 30 seconds.
Kling 4.0 Omni Reference: 15 inputs; kling-3 on Sume takes none
Kling 4.0 Omni Reference allows up to 15 combined references. On Sume, kling-3 takes none; wan-3.0 and minimax-h3 list image, video and audio caps.
Kling 4.0 multiple keyframes: ten, versus Sume's two frames
Kling 4.0 announces up to 10 keyframes. Sume's video routes take a first and last frame; longer chains mean separate clips cut and joined.
Kling 4.0 video editing: five video inputs, Sume edits one
Kling 4.0 editing takes up to five video inputs. Sume's Omni edit route takes one video_url and cannot combine it with references.
Kling 4.0 prompt length: 8,000 tokens vs Omni's 20,000 characters
Kling 4.0 allows prompts up to 8,000 tokens. Sume documents a 20,000-character prompt cap for gemini-omni-flash-1.1; tokens and characters differ.
Gemini Omni reference video length: 3 seconds per clip on Sume
On Sume, each Gemini Omni Flash reference video can be at most 3 seconds, with up to 3 clips. Trim longer footage first, then address clips as VIDEO_REF tags.
LTX 2.5 API: check the Sume catalog before you send a model id
LTX-2.5 has its own API and open weights. On Sume, send only ids that GET /v1/videos/models lists; an unknown id returns model_not_found. How to check and pick.
Seedance 2.5 reference limit: BytePlus says 50, Sume varies by model
BytePlus allows up to 50 multimodal references for one Seedance 2.5 clip. Sume documents limits per model, so read the catalog for the id you send. Examples.
Grok Imagine image edit limit: xAI 5 sources, Sume catalog
xAI's Aug 28 release notes raise image editing to 5 source images. On Sume, Grok is edit-capable with n of 1; read input_references per model.
Nano Banana Google Search grounding: not a Sume parameter
Google documents Search grounding for its Gemini image models. Sume lists Nano Banana 2 but no grounding field, and unlisted fields return 400.
Nano Banana thinking mode and thought images on Sume
Google's Gemini 3 image models use thinking mode and uncharged thought images. Sume lists no thinking field, and you pay only for completed images.
Nano Banana 14 reference images vs Sume's 10 input_references
Google says Gemini 3 image models mix up to 14 reference images. Sume's Nano Banana models take up to 10 input_references; ChatGPT Image 2.5 takes 16.
Odia and Urdu text to speech API: the language codes
Cartesia's Sonic 3.6 adds Odia (`or`) and Urdu (`ur`). On Sume, send the code in `language`, pin `sonic-3.6`, and check the voice before you pay.
Lyria RealTime API: streaming music vs a Sume file job
Lyria RealTime streams steerable instrumental music over a WebSocket. Sume's Music Router returns a finished audio file per job. Here is how they differ.
Lyria 3 Clip 30-second music API: ids Sume lists
Lyria 3 Clip always makes 30 seconds. Sume does not list it; ask for a 30-second track in the prompt with sume/music-auto, lyria-3.5 or lyria-3-pro.
Kazakh speech to text API: Nova-3 and Sume language_code
Deepgram added Kazakh to Nova-3 on Sep 3, 2026. Sume STT 1.0 takes an optional language_code hint, or auto-detect. How to send audio and check the output.
TikTok Symphony with Seedance 2.5: 30-second AI video ads
TikTok Symphony now generates up to 30 seconds with Seedance 2.5, in select markets. The same 30-second length is available by API on Sume as seedance-2.5.
Muse Image API: how to check what Sume's image catalog lists
Runway lists a muse_image model at 1 credit per image. For Sume, read the live image catalog instead of assuming; endpoint pricing lines are what you pay.
Seedance 1.5 Pro retires Nov 11: which Seedance ids Sume lists
ByteDance retires Seedance 1.5 Pro on November 11, 2026. Sume's video docs list seedance-2.5 and seedance-2; use bare catalog ids and check the models endpoint.
HeyGen reference to video: 9 images, 3 videos, 3 audio
HeyGen's heygen-video-1 reference mode takes 9 images, 3 videos and 3 audio files, 12 in total. Here is how Sume's reference limits compare.
HeyGen text to video API: 5-15 s, 768p vs Sume durations
heygen-video-1 makes 5-15 second clips at 480p or 768p from a 5,000-character prompt. Sume lists durations and resolutions per model in its catalog.
HeyGen ElevenLabs v3 model_id per request vs Sume TTS
HeyGen's speech endpoint takes settings.model_id such as eleven_v3 per request. Sume TTS 1.0 hides model ids; its separate TTS Router lists models explicitly.
Tavus Phoenix-4.5: photo rules vs a Sume photo avatar
Tavus Phoenix-4.5 starts a face from a photo in minutes and allows glasses, jewelry and hair. Sume creates an avatar from a public HTTPS image URL.
OmniHuman 1.5 API: native 1080p vs Sume avatar 720p
BytePlus says OmniHuman 1.5 outputs native 1080p from one image plus audio. Sume's Avatar Video currently outputs 720p; its video models list 1080p separately.
Mirage Avatar X: a 10-second AI twin vs Sume avatar inputs
Captions' Mirage Avatar X powers its avatars and AI twins, and a twin needs ten seconds of footage. Sume avatars come from a prompt, a profile or an image.
HeyGen photo avatar hand gestures vs Sume Motion Control
HeyGen's motion_prompt still needs an animation reference for Avatar V photo avatars. On Sume, body motion is a separate Motion Control route, not a prompt.
GPT Image 2 supported aspect ratios on Sume: 5:4, 9:8, 4:5
On Sume, gpt-image-2 accepts 5:4, 9:8 and 4:5 on top of the common ratios, plus custom pixels with a 3:1 limit. The exact list and the 9:8 size to send.
Generative Extend any aspect ratio: Sume video ratios
Premiere's Generative Extend now takes any aspect ratio. Sume's gemini-omni-flash-1.1 makes 16:9 or 9:16 clips; for other shapes, conform with Timeline fit.
Voice cloning API: clone once in the app, speak via the API
Sume has no API route that creates a voice clone. You clone once in the app, then send the voi_ id to the text to speech API on every call.
How to colorize a black and white video with AI
Colorize a black and white video with an AI video-to-video edit: send the clip and a prompt naming the colors. The model invents them.
AI outfit change video: change clothes in a clip with AI
Change someone's outfit in an existing video with an AI video-to-video edit: name the garment, what it becomes, and what must stay the same.
Batch edit photos with AI: one edit across many photos
To batch edit photos with AI, send the same edit prompt once per photo, with that photo as the reference. How to script it, pace it, and what it costs.
AI sky replacement: swap the sky and keep the photo
AI sky replacement: send the photo to an image-edit model, describe only the new sky, and list what stays. Then check roof and tree edges. Cost and limits.
Remove shadow from photo with AI: edit it or cut it out
To remove a shadow from a photo with AI, send the photo to an image-edit model, name the one shadow to remove, and list what stays. Prompts, cost, limits.
Kling 2.6 vs 3.0: length, resolution, audio and price
Kling 3.0 makes 3–15 s clips up to 4K with audio and multi-shot; 2.6 makes 5 or 10 s shots at 720p or 1080p. Kling's own specs and prices, dated.
AI avatar video aspect ratio: square, 3:4 and vertical 9:16
Sume's avatar video endpoint takes aspect_ratio 1:1, 3:4, 9:16, 4:3 or 16:9, defaulting to 9:16, at 720p. Which value to send for square or vertical.
AI image negative prompt: what to do when the API has no field
Sume's image API has no negative prompt field. Describe what you want instead, edit with a mask, and keep references. The fields that do exist.
AI image generator with readable text: which Sume models to try
Which Sume image models have a vendor claim about text in images, what each vendor says, and the quality setting Sume's docs suggest for dense text.
Does Lyria 3.5 music carry a SynthID watermark?
Google says all Lyria 3.5 audio includes a SynthID watermark. What that means for tracks made through an API, and what Sume's docs do and do not say.
AI video multiple faces consistency: Luma's 8-face limit, Sume's caps
Luma Ray3.2 lists facial performance tracking for up to 8 faces. Sume has no such setting; the limit is how many reference images each video model accepts.
Why AI video models do not lip sync to a voiceover, and what to use
Sume docs: video models do not lip-sync to generated speech or a voice-over. For a talking face use Avatar video or the lip-sync endpoint (still plus audio).
Cartesia Sonic 3.6 API: which model id to send
Send sonic-3.6 for the latest stable Sonic 3.6, a dated id to freeze it, or sonic-preview for beta. Which of these ids Sume's TTS Router lists.
ChatGPT Images 2.5 vs GPT-Image-2.5: which name is the API?
ChatGPT Images 2.5 is OpenAI's product; GPT-Image-2.5 Flare and Sunburst are the API models. How the names map to Sume ids and which features stay in ChatGPT.
Does ChatGPT Images 2.5 add a watermark? C2PA explained
OpenAI says ChatGPT Images 2.5 uses C2PA metadata and invisible watermarking to identify its images. What that means for files you get through an API.
Claude Sonnet 5.5 or Opus 5.5 for an agent that calls a video tool?
Sonnet 5.5 and Opus 5.5 differ in price and release date on Anthropic's pages. Which facts matter when the tool is Sume's video generation, and what stays same?
Text to speech Korean API: 90+ languages claim vs what Sume lists
Eleven v4 says 90+ languages. Sume's TTS schema publishes no language count, only a language field and five Sonic ids. Request Korean or Japanese and test it.
Eleven v4 audio tags [laughs]: how to use them, and Sume's controls
Eleven v4 reads inline tags such as [laughs] and [light rain] in the text. Sume's TTS schema has no tag syntax; it has speed, volume and emotion controls.
ElevenLabs Eleven v4 API: what it is and how to reach it
Eleven v4 and v4 Turbo launched September 28, 2026 on ElevenLabs' own API. What ElevenLabs says they do, and which TTS ids Sume's router lists.
FLUX.2 dev commercial use: what the model card says
FLUX.2 [dev] weights carry the FLUX non-commercial license, yet the card says outputs can be used commercially as that license describes. The exact wording.
FLUX.2 flex text rendering: prompt tips and the Sume model id
Black Forest Labs positions FLUX.2 [flex] for text and fine detail. How its typography guidance reads, and how to call black-forest-labs/flux.2-flex on Sume.
FLUX.2 hex color prompt: how to write it, with an API call
Black Forest Labs says FLUX.2 matches hex codes in prompts. The syntax it documents, the limits it admits, and a flux.2-pro call on Sume.
FLUX.2 pro vs Nano Banana Pro API: request specs side by side
Request parameters that differ between black-forest-labs/flux.2-pro and google/nano-banana-pro on Sume: resolution tiers, aspect ratios, references and price.
FLUX.2 prompt guide: structure, length and no negatives
Black Forest Labs' FLUX.2 prompt rules: subject, action, style, context; 30-80 words; no negative prompts. Which apply to flux.2-pro on Sume.
FLUX 3 vs FLUX 2: which one you can call on Sume today
FLUX 3 vs FLUX 2 for image work: BFL's notes start FLUX 3 with video, and Sume's image catalog serves FLUX.2 Pro and Flex. What that means for stills.
FLUX 3 video 20-second clips: what Sume's video API offers
FLUX 3 Video makes up to 20 s clips at 1920x1088. Sume does not list it, but seedance-2.5 and wan-3.0 accept 20 s requests. Durations by model.
Gap or click when joining audio files: use wav, not mp3
Sume's Timeline audio joins up to 20 Sume-hosted parts with no silence at the seams. Its docs say to keep wav, because mp3 adds padding at every edge.
Gemini Live Avatar vs a video avatar API: live or rendered?
Gemini 3.8 Live Avatar streams a lip-synced face in a conversation. Sume's avatar video renders a finished clip from a script. Which job needs which.
Gemini Live Avatar: 97 languages and SynthID, explained
Google says Gemini 3.8 Live Avatar covers 97 languages and adds SynthID to audio and video. What each claim covers, and what it says about other avatar tools.
Gemini Omni 1.1 Flash 360p drafts: what a cheap preview costs
Gemini Omni Flash 1.1 can render 360p previews. On Sume a 360p second is billed at 30% of a 720p second, so drafts cost less than finals.
Gemini Omni Flash 4K: clip length, upscaling and price
Gemini Omni Flash 1.1 renders 4K clips of 3 to 10 seconds on Sume, and Google labels its 4K output upscaled. Length versus Veo 3.1, plus cost.
gemini-omni-flash-preview shuts down September 30: what to change
Google's deprecations list gemini-omni-flash-preview with a 2026-09-30 shutdown and gemini-omni-1.1-flash as its replacement. What changes, and the Sume id.
Gemini Omni Flash prompt guide: one shot, audio, text
Google's Omni Flash prompt tips: ask for a single continuous shot, put negatives in the prompt, describe the audio, spell out on-screen text. Plus a Sume call.
Gemini Omni Flash vs Veo 3.1: which does Google recommend when
Google's video page names Gemini Omni Flash the default, Veo 3.1 for scene extension, last-frame control or legacy pipelines. Facts side by side, plus Sume ids.
Gemini Omni prompt timecodes: [0-3s] and scene cuts
Gemini Omni Flash takes timing in plain words or a [0-3s] timecode syntax, so you can script cuts inside one clip. Google's examples and a 10-second Sume call.
Gemini Omni video edit prompts that keep everything else the same
Google says short prompts work best when you edit a video with Gemini Omni Flash, and to add Keep everything else the same. Examples, limits and a Sume call.
Gemini Omni reference video: is the audio used? No
Gemini Omni Flash accepts video references but not audio: Google says audio in a reference clip is ignored. Limits, Sume's fields, and models that take audio.
Does Gemini Omni video have a SynthID watermark?
Google says all Gemini Omni Flash videos include an invisible SynthID watermark. What that means for API clips, YouTube disclosure, and what Sume's docs say.
Google Flow video length: 4 to 10 seconds by model
Google Flow makes 4, 6 and 8 second clips with Veo 3.1 and 4 to 10 seconds with Gemini Omni Flash 1.1. Length by model and mode, from Google's help page.
Does Sume Auto use GPT Image 2.5? What sume/auto picks for images
Sume's docs say Auto image routing continues to use Flare, GPT Image 2.5. Sume never says which family ran on a call, so pin openai/gpt-image-2.5 if it matters.
GPT Image 2.5 Flare vs Sunburst: what each model page says
OpenAI calls Flare its model for everyday image generation and Sunburst its most capable for generation and editing. What each page lists, and both ids on Sume.
GPT Image 2.5 quality levels: low, medium, high, xhigh, max and auto
GPT Image 2.5 has six quality values: auto, low, medium, high, xhigh and max. What each does to price on Sume and which one runs when you send nothing.
GPT Image 2.5 release date and model ids: Flare and Sunburst
OpenAI's GPT-Image-2.5 Flare and Sunburst carry the snapshot date 2026-09-08. The model ids, dated snapshots, and how Sume names the same two models.
GPT Image 2.5 resolution: the size rules and the 4K ceiling
GPT Image 2.5 takes custom sizes: both edges a multiple of 16, longest edge 3840, 655,360 to 8,294,400 pixels. What that means for 1080p, 1440p and 4K.
Grok Imagine image API: the x-ai/grok-image id on Sume
Sume lists Grok Imagine as x-ai/grok-image on its image API: thirteen aspect ratios (no 4:5), one reference image for edits, and a $0.025 price line per image.
Grok Imagine aspect ratio: 21:9 and 5:2 on xAI vs Sume
xAI added 21:9 and 5:2 to Grok Imagine image on Aug 28. Which ratios Sume's grok-image accepts, what the 400 looks like, and a call that works.
Grok Imagine Video 1.5 reference images API: xAI vs Sume
xAI's API takes up to seven reference images, text-to-video and 1080p for Grok Imagine Video 1.5. Sume's API reference lists it as first-frame image-to-video.
Hailuo 3.0 release date: MiniMax H3 launched 2026-07-31
Hailuo 3.0 is the name people use for MiniMax H3, which MiniMax released on 2026-07-31. What the vendor pages call it, and the ids that reach it on Sume.
How much VRAM for AI video generation? Numbers from model cards
From 14 GB to 80 GB: the VRAM figures Tencent, Wan-AI and Genmo publish for their open video models, and what each number was measured with.
HunyuanImage 3.0 API: open weights, no listed Sume model
HunyuanImage 3.0 is an 80B-parameter open-weights image model from Tencent. Sume's image docs do not list it; here is what the card says and the hosted route.
HunyuanVideo 1.5 low VRAM: 14 GB with offloading
Tencent's HunyuanVideo-1.5 card lists 14 GB as the minimum GPU memory with offloading on. The OOM settings and step-distilled option it names.
HunyuanVideo API: is there a hosted one, or only weights?
HunyuanVideo is published as downloadable weights. Sume's docs list no HunyuanVideo API, so here is what running it takes and the listed video ids.
Ideogram 4.0 API: request shape and what Sume lists
Ideogram 4.0 has its own endpoint with text_prompt or json_prompt. Sume's image catalog lists Ideogram V3 only; here is how the two differ.
Imagen 4 API shut down in the Gemini API: what Sume's catalog lists
Google says Imagen is shut down in the Gemini API and points to Nano Banana. Sume's image catalog lists google/imagen-4-fast, imagen-4-ultra and Nano Banana ids
AI video generator for Instagram Reels: 9:16 models and durations
Which Sume video models take 9:16 and for how many seconds: seedance-2.5 and wan-3.0 reach 30, minimax-h3 5 to 15, gemini-omni-flash-1.1 3 to 10, and sume/auto.
Kling 3 4K API: Kling's own tier and what Sume lists
Kling 3.0 lists 4K on Kling's own capability map, but Sume's kling-3 lists 720p and 1080p and prices no resolution tier. Sume's 4K route: gemini-omni-flash-1.1.
Kling 3 duration and aspect ratio limits: Kling's own vs Sume's
Kling's own map lists 3 to 15 seconds for Kling 3.0; Sume's kling-3 takes 4 to 15 seconds at 16:9, 9:16 or 1:1. Values outside the list are refused.
Kling 3 first and last frame API: request, limits and a gotcha
On Sume, kling-3 takes a first and optional last frame via frame_images, for 4-15 seconds. Send frame one in the shape you want; aspect_ratio is text-only.
Kling 3 lip sync with your own audio: what each API does
Kling lists lip sync driven by text or audio. Sume's kling-3 takes no audio input, only a generate_audio switch; models with audio references are listed.
Kling 3 native audio: what the on and off price difference is
On Sume, kling-3 costs $0.14 a second silent and $0.21 with audio. Audio is on unless you send generate_audio false, so the default is the higher price.
Kling 4.0 API: what Sume lists and what to use today
Kling 4.0 API availability could not be confirmed from Kling's own pages on 2026-09-29. Here is what Sume's docs list today for video, and where Kling appears.
Kling motion control API in Python: submit, poll, fetch
Call Kling 3.0 motion control from Python with requests: submit with an Idempotency-Key, poll the status URL until terminal, then fetch the result when ready.
Kling motion control camera movement and orientation
In Kling motion control, character orientation decides whether the camera follows the video or the image. What Kling says, and Sume's character_orientation.
Kling motion control face consistency: element binding
Kling 3.0 Motion Control keeps a face steady by binding a facial element to the character image. How it works, and what Sume's endpoint takes instead.
Kling motion control with multiple people in the video
Kling motion control animates one character. With two or more people in the reference, it uses the one with the largest share of the frame.
Kling motion control not working: causes and fixes
A short, cut-off or wrong-person Kling motion control result usually traces to the reference video. Kling's causes, and the errors Sume's endpoint returns.
Kling motion control prompt: what it can change
In Kling motion control the video supplies the movement and the prompt covers background and looks. Kling's examples, and Sume's 2,000-character prompt.
Kling motion control reference video requirements
Kling asks for one character in one continuous shot, 3 to 30 seconds, short edge 340 px or more. Which limits Sume's endpoint also enforces.
LTX 2 open source: what Lightricks released, and the license
LTX-2 is an audio-video model with open weights under the LTX-2 community license. What the Hugging Face cards list, and why Sume's catalog has no LTX.
Luma Ray 3.2 20 seconds 1080p: how Sume's catalog limits read
Luma says Ray3.2 makes up to 20 seconds at 1080p. In Sume's video docs, seedance-2.5 is the one model stated to accept 20 seconds at 1080p.
Luma Ray 3.2 API: 16 keyframes, and Sume's two-frame route
Luma says Ray3.2 takes up to 16 keyframes per clip. Sume lists no Luma model; chain its first and last frames to cover more key images.
Luma Ray3.2 modify: what is confirmed, and Sume's edit route
Luma's Ray3.2 notes list keyframes, 1080p, HDR and reframe but no quotable modify details. Sume's video edit route is gemini-omni-flash-1.1 with video_url.
Lyria 3 Pro or Lyria 3.5: which model id do I send?
Sume's Music Router accepts sume/music-auto, lyria-3.5 and lyria-3-pro. What each id does, how to pin one, and what Google lists for the models.
Lyria 3.5 API: model id, request and how to call it
Lyria 3.5 is in the Gemini API as lyria-3.5. Here is what Google's page says about it and how to call it from Sume with one music request.
AI music generator with vocals: Lyria 3.5 lyrics by API
Lyria 3.5 can sing. How to ask for vocals or an instrumental, steer lyrics with section tags, and read the lyrics back from a Sume music job.
Lyria 3.5 release date: where it is available
Google announced Lyria 3.5 in the Gemini app on 2026-09-04. Where Google says you can use it, and where Sume lists it.
How long is a Lyria 3.5 song, and how do I set the length?
Lyria 3.5 makes songs of a couple of minutes, and length is set in the prompt. What Google says, what Sume rejects, and prompts that steer duration.
Midjourney V8.2 API: does Sume list a Midjourney model?
Sume's image catalog has no Midjourney model, so a Midjourney id returns 404 model_not_found. Read the live list with GET /v1/images/models and try sume/auto.
2K AI video generator API: MiniMax H3 at 2K on Sume
MiniMax H3 makes video up to 2K. On Sume you ask for resolution 2K on minimax-h3, an upscale of native 768p. Request, price for 10 seconds, and limits.
MiniMax H3 languages: which spoken languages does it support?
MiniMax says H3 has stable support for 11 dialogue languages and partial support for others. Sume's docs list no language set, so test yours first.
MiniMax H3 Max 1080p: a latent refinement from native 768p
MiniMax H3 Max on Sume offers 480p, 768p and 1080p. The 1080p tier is a latent refinement from native 768p. What that means for price and output checks.
What is MiniMax H3 Max? The post-trained variant, explained
MiniMax H3 Max is a variant post-trained by fal.ai on MiniMax H3 for faster generation. Its resolutions, lengths and modes, and how Sume lists it.
MiniMax H3 Max lip sync API: a still plus audio, 5 to 14.8 seconds
Sume runs MiniMax H3 Max lip sync at POST /v1/minimax/h3-max/lip-sync: send a still and Sume-hosted audio of 5 to 14.8 seconds. Body, resolutions and price.
AI video with native stereo sound: MiniMax H3 audio through the API
MiniMax H3 generates native stereo sound in the same pass as the video. On Sume audio is always on, generate_audio false is refused, and audio steers.
MiniMax H3 open weights on Hugging Face: what is in the release
MiniMax H3 has a model card on Hugging Face: two checkpoints, a 33B-parameter Transformer, a community license and a 4-GPU serving example. What to check first.
MiniMax H3 cache and sparse attention: what the open release has
MiniMax's H3 open release ships full-attention inference only; sparse attention comes later. About 13B parameters can be cached, not loaded.
AI video editing with a text prompt: MiniMax H3 and Sume's edit path
MiniMax H3 is described as editing existing video from instructions. What the vendor says, what Sume's H3 ids accept, and the id with an edit field.
Mochi video model: what Mochi 1 is, needs and can't do
Mochi 1 preview is Genmo's Apache 2.0 open video model: 480p output, about 60 GB VRAM on one GPU, and it is not in Sume's video catalog.
Nano Banana 2 Lite API: what Google shipped and what Sume lists
Nano Banana 2 Lite is Google's gemini-3.1-flash-lite-image model. What Google says it does, and which Nano Banana models Sume's image API lists today.
Nano Banana Pro custom aspect ratio: what Sume does
Nano Banana Pro on Sume takes 11 native aspect ratios. A custom ratio or WxH size is snapped to the nearest one. Which, and how to check.
Nano Banana Pro vs Nano Banana 2: which id to send on Sume
Nano Banana Pro and Nano Banana 2 share tiers and 10 references on Sume; they differ in extra aspect ratios and in which tiers change the price.
Nano Banana quality parameter: why quality returns 400
Sending quality to Nano Banana 2 or Pro on Sume returns 400 unsupported_parameter. What quality does elsewhere, and what to change instead.
Open source AI video generator with audio: LTX-2 and MiniMax H3
Two open-weights video models make sound with the picture: LTX-2 and MiniMax H3. What each page says, and how a hosted API reports audio.
Open-source video model vs API: which to use for Wan-class video
Weights you run yourself, or a hosted video API? What the choice changes for cost, setup and limits, with Wan 3.0's per-second API price as the worked example.
Qwen Image 2.1 API: open weights, and what Sume lists
Qwen-Image-2.1 is an open-source 7B image model on Hugging Face with no inference provider. Sume lists qwen-image and qwen-image-max instead.
Qwen Image 3.0: does Sume list it? A catalog check
Sume lists qwen/qwen-image and qwen/qwen-image-max, and nothing named 3.0. How to check the live catalog for a new Qwen id and what an unknown id returns.
Qwen Image license: is Qwen-Image open source under Apache 2.0?
The Qwen-Image model card says the weights are Apache 2.0 and were released on 2025-08-04. What that covers, and how the hosted qwen ids on Sume differ.
Qwen Image Max API on Sume: text-only, and how it differs
qwen/qwen-image-max on Sume is text-to-image only and rejects reference images with a 400. Price, ratios, a working call, and how it differs from qwen-image.
Recraft V4.1 API on Sume: check the catalog for the id
Sume lists recraft/recraft-v4, not a V4.1 id. How to check the live catalog for a newer Recraft, and what the listed model takes: text only, webp, $0.05.
Recraft V4 SVG: can you get vector output through Sume?
Recraft says V4 can make editable SVG. Sume's recraft/recraft-v4 advertises webp output only. What that means, plus a working call.
Runway Media Router and sume/auto: what Sume's router does
Looking for a Runway Media Router equivalent? Sume's video router is sume/auto: it picks the model, never says which ran, and clips run 3 to 10 seconds.
Does generate_audio change Seedance 2.0's price?
No. fal says Seedance 2.0 audio costs the same on or off, and Sume's Seedance price has no audio input: seedance-2 reserves about $0.38 per 720p 16:9 second.
Seedance 2.0 max length: 15 seconds, and how to go longer
Seedance 2.0 clips run 4 to 15 seconds on Sume and on fal. For 16 to 30 seconds use seedance-2.5 ($17.34 at 720p) or chain clips with first_frame.
What is Seedance 2.0 Mini, and where can you run it?
Seedance 2.0 Mini is a Seedance 2.0 model that CapCut and fal list. On Sume it is the id seedance-2-mini, 4–15 s clips, about $0.19 per 720p second.
Does a reference video change Seedance 2.0's price?
Yes. A reference video adds 15 assumed input seconds at 0.6× on Sume, so a 10 s 720p clip on seedance-2 reserves $5.67, not $3.78.
Seedance 2.0 resolution in pixels: 480p, 720p and 1080p by ratio
Seedance 2.0 720p at 16:9 is 1280×720 and 1080p is 1920×1080. The full pixel table for six aspect ratios, as fal lists it and Sume prices it, with no 4K.
Seedance 2.5 3D blockout camera control: clay renders as a reference
Seed describes clay-render referencing, a textureless 3D model that blocks camera and pose. Sume has no clay mode; you send the render as a video reference.
Seedance 2.5 aspect ratios: 9:16 vertical, 21:9 and the rest
Seedance 2.5 on Sume accepts 21:9, 16:9, 4:3, 1:1, 3:4 and 9:16. Set aspect_ratio explicitly; 3:2 is rejected. Ratios, errors and the price effect.
Seedance 2.5 audio reference: how to send an audio clip
Seedance 2.5 accepts an audio clip as a reference, even without an image or video. The audio_url request on Sume, the vendor's file limits and what to expect.
Seedance 2.5 image to video: first frame and last frame
Send a first_frame, or a first_frame and last_frame, with seedance-2.5 on Sume. Rules for frame_images, how it differs from input_references and what to set.
Seedance 2.5 omni reference: how @image, @video and @audio tags work
Seedance 2.5 prompts point at references with tags such as @Image 1. Sume rewrites lowercase tags like @image1 to the casing the model expects. Examples.
Seedance 2.5 50 references: how many can you use on Sume?
BytePlus lists 50 Seedance 2.5 references (30 images, 10 videos, 10 audio clips). Sume's API accepts 12 input_references per request for seedance-2.5. Compared.
When was Seedance 2.5 released, and where can you use it?
ByteDance Seed launched Seedance 2.5 on 2026-07-31 in its own apps. The model id seedance-2.5 is in Sume's video catalog. Dates and access, read 2026-09-29.
Seedance 2.5 video editing: green screen, camera angle, timestamps
ByteDance says Seedance 2.5 edits video by timestamp, incl. green screen and camera angle. What BytePlus documents for edits and what Sume's API lists today.
Seedance 2.5 vs 2.0: what changed in duration and references
Seedance 2.5 raises the clip to 30 seconds and references to 50 in BytePlus's docs. The 2.0 vs 2.5 table and how Sume's own limits differ, read 2026-09-29.
Seedance 2.5 vs Gemini Omni: length, references and editing
Seedance 2.5 and Gemini Omni Flash compared on published specs: 30 vs 10 seconds, reference rules, extension and edit mode. Ids on Sume and on Google's page.
Seedance 2.5 vs Kling 3.0: durations, references and audio
Seedance 2.5 and Kling 3.0 compared on the specs their own pages and Sume's catalog publish: length, resolution, references, audio. No winner, just the table.
Seedream 5.0 Pro API: Sume lists 5.0 Lite, not Pro
Sume's catalog has bytedance-seed/seedream-5-lite, 4.5 and 4.0, and no Seedream 5.0 Pro id. What a Pro id returns and which listed model to call instead.
Cartesia Sonic 3 languages: 44 in Sonic 3.6, how to set one
Cartesia says Sonic 3.6 speaks 44 languages, including new Odia and Urdu. How its language and locale fields work, and Sume's language field.
Stable Audio 3 open weights: run them yourself or call a hosted API
Stable Audio 3 Small SFX, Small and Medium are open-weight; Large is on Stability's API. Sume's music route lists Lyria ids only, so weights mean self-hosting.
Stable Audio 3 max length: six minutes, and how to reach it on Sume
Stability says Stable Audio 3 Medium and Large pass six minutes. Sume's Lyria music runs up to a few minutes; join separate takes for more with Timeline audio.
Text to speech API with emotion, speed and volume controls
Sume's text to speech API takes generation_config: speed 0.6 to 1.5, volume 0.5 to 2.0 and an optional emotion guide of up to 64 characters.
Text to speech sample rate: which output_format to pick
Sume's TTS output_format takes mp3, wav or raw, six sample rates from 8000 to 48000 Hz and four PCM encodings. The default, and when to send wav.
Veo 3 shutdown: which Gemini API models retired and what replaces them
Google retired veo-3.0-generate-001, veo-3.0-fast-generate-001 and veo-2.0-generate-001 on 2026-06-30. Its listed replacements are the Veo 3.1 preview models.
Veo 3.1 4K API: 8 seconds only, and 4K options on Sume
Veo 3.1 makes 4K video only at 8 seconds, and not on the Lite model. On Sume, gemini-omni-flash-1.1 lists 4K for 3 to 10 seconds.
Veo 3.1 API: how to call it, and what Sume lists instead
The Veo 3.1 API is Google's, called through the Gemini API with preview model codes. Sume does not list Veo; here are the catalog models with the same inputs.
Veo 3.1 extend video, and how to chain clips on Sume
Veo 3.1 extends only videos Veo made, 7 seconds at a time. Sume has no extend call, so you chain clips from a last frame or pick a model with a longer limit.
Veo 3.1 first and last frame: how the API works
Veo 3.1 takes a first image and a last image and generates the motion between them. Here is Google's request shape and where the same input works on Sume.
Veo 3.1 Lite, Fast or standard: how to choose
Veo 3.1 has three preview models: standard, Fast and Lite. Lite drops 4K and extension; Fast targets speed. What each does, plus Sume's tiered Seedance.
Veo 3.1 reference images: three max, and the 8-second rule
Veo 3.1 takes up to three reference images, and a request with them must run 8 seconds. Sume does not list Veo; its reference-capable models take more.
Veo 3.1 vs Kling 3.0: how to choose by inputs and limits
Google's Veo 3.1 limits next to the kling-3 entry in Sume's catalog: clip length, resolution, references and audio. Sume lists kling-3 and does not list Veo.
Veo 4 release date: what Google's Veo pages list today
Google's Gemini API pages list Veo 3.1 and its Lite preview and name Gemini Omni Flash the default video model. No Veo 4 date appears; here is what does.
Choosing an AI video API as a developer: a technical checklist
Choose an AI video API on job model, not demos: async submit and poll, idempotent retries, webhooks, live capability discovery, a billing model you can read
AI video with audio: which models always add sound, which are optional
On Sume, minimax-h3, minimax-h3-max and gemini-omni-flash-1.1 always add native audio; kling-3, Seedance and Wan make it optional; grok-imagine-video-1.5 none.
sume/auto or a pinned video model: how to decide
Use sume/auto when you accept 3 to 10 second clips at 16:9 or 9:16 and do not care which family runs. Pin a model id for a specific input, length or audio.
Which AI video model should I use? A checklist by input and output
Pick an AI video model by what you must send and get back: frames, references, audio, length, resolution. This checklist maps each need to Sume catalog ids.
Wan 3.0 open source: weights on Hugging Face or API only?
fal says Alibaba's published Wan weights stop at Wan 2.2, and Wan 3 is an API model. What that means for Hugging Face searches, and the wan-3.0 id Sume hosts.
Wan 3.0 1080p: how to request full HD from the API
Wan 3.0 outputs 480p, 720p or 1080p. Send resolution 1080p to wan-3.0 on POST /v1/videos, up to 30 seconds, with audio. See the request and the price.
Wan 3.0 2-second clips: the shortest video length and what it costs
Wan 3.0's floor is 2 seconds, shorter than the 4-second minimum on Seedance 2.x models. Send duration 2 to wan-3.0; at 720p it costs $0.25 before the agent fee.
Wan 3.0 30-second video: one clip, no stitching
Wan 3.0 makes a single clip of up to 30 seconds with audio. Set duration to 30 on wan-3.0 in POST /v1/videos. Here is the request, the cost, and the limits.
Wan 3.0 document to video: what the model reads and what Sume passes
Alibaba's Wan 3.0 can read an uploaded document to make a video. On Sume's video API today wan-3.0 takes prompts, frames and media references, not a file input.
Wan 3.0 first and last frame: animate between two images
Wan 3.0 can make a clip that starts on one image and ends on another. On Sume, send frame_images with first_frame and last_frame to wan-3.0; last needs first.
Wan 3.0 omni reference video: images, clips and audio in one prompt
Omni reference means one request carries mixed references. Wan 3.0 takes up to 10 images, 5 videos and 5 audio tracks; on Sume, send them as input_references.
Wan 3.0 reference limits: how many images, videos and audio clips
Wan 3.0 reference-to-video takes up to 10 images, 5 video clips and 5 audio tracks. See the per-type caps, what Sume rejects with unsupported_capability, why.
Wan 3.0 thinking mode: why document and web page input needs it
fal says Wan 3.0 needs thinking mode to read a document or web page; Alibaba says prompt_extend must be true. What each means, and why Sume's wan-3.0 skips it.
Wan 3.0 vertical video: 9:16 for Reels, Shorts and TikTok
Wan 3.0 supports 9:16. Send aspect_ratio 9:16 to wan-3.0 for a vertical clip of 2 to 30 seconds at 480p, 720p or 1080p. Accepted ratios and cost.
Wan 3.0 vs MiniMax H3: clip length, ratios and reference caps
Wan 3.0 runs 2 to 30 s at up to 1080p; MiniMax H3 runs 5 to 15 s at 480p or 768p. Where they differ on Sume: ratios, reference caps and audio inputs.
Wan 3.0 vs Seedance 2.0: which model to call when
Wan 3.0 and Seedance 2.0 are both on Sume's video API. Wan runs 2 to 30 s and bills per second; Seedance 2.0 runs 4 to 15 s with a 21:9 frame. Pick by the job.
Wan 3.0 web page to video: link input and how to do it on Sume
Wan 3.0 can read a public web link to make a video on Alibaba's API. Sume's wan-3.0 has no link field, so fetch the page yourself and send text and images.
Is there one API for Kling, Seedance and Veo with a single bill?
Yes. fal, Replicate, Runway, Higgsfield and Sume bill several video models on one account. Which list Kling, Seedance and Veo, with units and limits.
Kling 3.0 API: text or image to video, limits and price
Kling 3.0 has an API: Kling's own, and multi-model APIs such as Sume's, where it is kling-3: 4–15 second clips from text or frames, audio optional.
Grok Imagine video API: image to video, 4–15 seconds
Grok Imagine Video 1.5 is on Sume's video API as image-to-video only: a first frame and a prompt give a 4–15 second silent clip at 480p or 720p.
Kling 3.0 vs Seedance 2.0: inputs, limits and price
On Sume, Kling 3.0 and Seedance 2.0 both make 4–15 s clips from text or frames. Seedance adds references and six ratios, and bills per token.
Wan 3.0 vs Seedance 2.5: 30-second clips, inputs and price
Wan 3.0 and Seedance 2.5 both make clips of up to 30 s with audio, frames and references. Wan starts at 2 s and bills per second, Seedance per token.
Seedance 2.5 vs MiniMax H3: length, resolution, audio, price
On Sume, Seedance 2.5 makes 4–30 s clips at up to 1080p with optional audio; MiniMax H3 makes 5–15 s at native 480p or 768p, always with audio.
Kling AI vs MiniMax: Kling 3.0 and MiniMax H3 APIs compared
On Sume, Kling 3.0 makes 4–15 s clips with audio you can turn off and no references; MiniMax H3 makes 5–15 s, always with sound, and takes references.
Higgsfield vs Kling AI: studio or model maker?
Kling makes the Kling models and sells its own apps and API. Higgsfield is a multi-model studio that also runs Kling 3.0. Access and billing compared.
Runway API Seedance: calling Seedance 2.5 and 2.0 on Runway
Yes, Runway's API serves Seedance: seedance2_5, seedance2, seedance2_fast and seedance2_mini. Inputs, limits and credits, and other ways to call Seedance.
Kling vs Wan: Kling 3.0 and Wan 3.0 by API compared
Kling 3.0 makes 4–15 s clips with no references; Wan 3.0 makes 2–30 s clips and takes image, video and audio references. Inputs and price compared.
Seedance 2.0 vs Gemini Omni Flash: inputs, audio and price
Seedance 2.0 makes 4–15 s clips with optional audio and audio references; Gemini Omni Flash 1.1 makes 3–10 s clips up to 4K, always with sound.
Lip sync AI API options: photo or video input, limits, price
Lip sync APIs take a face and audio and return a talking clip. Some animate a photo, others redub an existing video. Inputs, limits and price units.
HeyGen text to speech API: endpoint, limits and price
HeyGen's API has a text to speech endpoint, POST /v3/voices/speech: up to 5,000 characters per call, catalog voices, word timestamps, $0.12 a minute.
Seedance 2.0 Fast vs Seedance 2.0 (and Mini): what differs
Seedance 2.0 Fast and Seedance 2.0 take the same inputs and 4–15 s lengths; the price differs: about $0.30 vs $0.38 a 720p second.
Seedance vs Seedream: ByteDance's video and image models
Seedance is ByteDance Seed's video model family; Seedream is its image model family. What each makes, takes, and costs through one API.
Kling vs Grok Imagine: Kling 3.0 and Grok Imagine Video 1.5
Kling 3.0 makes clips from text or an image, with an end frame and sound; Grok Imagine Video 1.5 animates one image, silent, for $0.0125/s.
AI video generator comparison table: price, length, sound
An AI video generator comparison on the same columns: billed rate, clip length, resolutions, sound and inputs for 11 video models, dated.
Seedance vs Sora 2: specs side by side after the shutdown
Sora 2 shut down on September 24, 2026. Its clip lengths, frame sizes, inputs, extensions and edits beside Seedance 2.0 and 2.5, which you can still call.
How to download Sora videos after the shutdown
To download Sora videos, open sora.chatgpt.com/sunset and click Export; OpenAI emails you when it's ready. Export soon: the data is deleted later.
Kling virtual try-on API: what it takes and returns
Kling's virtual try-on API takes one garment image and one person image and returns a try-on image, not a video. Fields, limits, price, and next steps.
Nano Banana MCP server for Claude: how to add one
To use Nano Banana in Claude, connect an MCP server that runs it. Which servers list it, how to add Sume's, and what a call looks like and costs.
Kling MCP: use Kling 3.0 from Claude Code or Cursor
Kling's own agent tool is a Skill. To call Kling 3.0 over MCP, connect a remote server that carries it, such as Sume's, which runs kling-3.
Seedance MCP: make Seedance 2.5 clips from Claude Code
To use Seedance over MCP, connect a remote server that runs it. On Sume's, generate_video takes four Seedance ids, with 30-second clips on 2.5.
Sora MCP server: why it stopped working and what to use
A Sora MCP server can't make video now: OpenAI shut the Sora API down on September 24, 2026. Point your MCP client at other video models instead.
FLUX MCP server: generate FLUX images from Claude
To use FLUX in Claude or Cursor, connect an MCP server that runs it. Which servers name FLUX, and how Sume's generate_image runs FLUX.2 Pro.
GPT Image MCP server: use GPT Image 2.5 in Claude or Cursor
To use GPT Image from Claude or Cursor, connect an MCP server that runs it. On Sume's, generate_image takes GPT Image 2.5 with masks and references.
Lyria MCP: generate music with Lyria 3.5 from Claude
Sume's hosted MCP server has a music_create tool that runs on Google Lyria 3.5 today: a prompt in, a job id back, an audio file on media.sume.com.
Dreamina vs Seedance: the app and the model it runs
Dreamina vs Seedance: Seedance is ByteDance Seed's video model; Dreamina is a creative app that runs it. When to use the app and when an API.
Runway ML alternatives for AI video: apps and APIs
Runway ML alternatives for AI video: fal, Higgsfield, Kling, Replicate and Sume compared on app vs API, models and billing, read 2026-09-28.
Multi-shot video generation: what it is and how to do it
Multi-shot video generation returns one clip with several cuts. Which APIs offer it (Kling 3.0, Runway) and how to build it shot by shot on Sume.
How does AI video generation work? Inputs, jobs, and limits
AI video generation turns a prompt, and optionally an image, into every frame of a short clip in one async job. What goes in, and why clips stay short.
AI video prompt JSON: what the keys actually do
A JSON prompt for AI video is still text: the model reads keys as words. Length, size and audio are request fields, not keys inside the prompt.
Seedance vs Grok Imagine: inputs, length, sound and cost
Grok Imagine Video 1.5 animates one image into a silent clip, billed per second. Seedance 2.x adds text, end frames, references and sound, billed by token.
FLUX.2 API pricing: Pro and Flex cost per image
FLUX.2 API pricing is per image. What FLUX.2 [pro], [flex] and the other variants cost on Black Forest Labs' API, and per image through Sume.
Is Kling AI Chinese? Who owns it and where it's based
Yes. Kling AI is developed by Kuaishou Technology, a Beijing-based company listed in Hong Kong. Who owns it, where its API runs, and other access.
Higgsfield AI vs Runway: apps, API, models and pricing
Higgsfield and Runway both sell a creative app and a video API billed in credits. How their models, API billing and job flow compare, from their pages.
Kling AI alternatives: other models, or Kling elsewhere
Kling AI alternatives: buy Kling 3.0 from fal, Higgsfield, Replicate, Runway or Sume, or switch to another maker's model. Dated table.
Higgsfield alternatives: studio, API and MCP compared
Higgsfield alternatives by the part you use: its studio apps, its API or its MCP link. fal, Kling, Replicate, Runway, Seedance and Sume, dated.
Runway Act-Two: what it does, API inputs and cost
Runway Act-Two applies an acted performance from a 3–30 second video to a character image or video. API fields, credit cost, and a Sume option.
Kling vs Runway: models, clip limits and API prices
Kling's API sells only Kling models; Runway's sells Gen-4.5 and Aleph 2.0 plus other labs' models. Clip limits, audio and per-second prices compared.
Runway Aleph 2.0 API: aleph2 inputs, limits and price
Yes: Aleph 2.0 is aleph2 on Runway's POST /v1/video_to_video. It edits a 2–30 s video from a prompt and keyframes at 28 credits a second.
Kling 3.0 vs Kling 3.0 Omni: inputs, limits and price
Kling 3.0 and 3.0 Omni share 3–15 s clips up to 4K with native audio. Omni adds reference and edit videos; 3.0 adds Motion Control. Prices compared.
Kling 3.0 prompt guide: length, shots, dialogue, negatives
A Kling 3.0 prompt can run to 3,072 characters and include negative wording. Kling's rules for shot lists, dialogue, languages and Elements.
Runway Gen-4.5 vs Seedance 2.0: inputs, length and price
On Runway's API, Gen-4.5 makes 2–10 s clips for 12 credits a second; Seedance 2.0 makes 4–15 s clips with audio for 36–150 credits a second.
Text to speech in Japanese: set the language to ja
For Japanese text to speech, send the script in kana and kanji and set the language to ja. Left out, Sume can read a kanji-only line as English.
Text to speech pronunciation: how to fix wrong words
Fix text to speech pronunciation: set the text's language, use a voice recorded in it, and respell tricky words. What Sume's TTS API checks for you.
How to change the color of an object in an image with AI
Send the photo to an AI image model, name the object and its new color, and list what must stay. One request per color, checked against the original.
AI image prompt examples: a template and 8 prompts to copy
A good AI image prompt names the subject, setting, style, light, and framing in a sentence or two. A template, 8 examples, and what goes in settings.
AI photo editing prompts: change one thing, keep the rest
An AI photo editing prompt says what to change and lists what to keep. The pattern, plus examples for background, light, color, style, and cleanup.
Image to image AI: turn your photo into a new picture
Image-to-image AI redraws your photo from a text instruction: a new style, background or color. What it changes, what it keeps, and how to run it.
How to change the background of a video with AI
Give a video-to-video AI model your clip and a prompt that names the new background and what must stay. How to do it on Sume and what to check.
How to remove an object from a video with AI
Name the object in a video-to-video AI edit prompt and say what stays. How to do it on Sume, how to swap or add objects, or blur them instead.
Video to anime AI: how to turn a clip into anime
To turn a video into anime with AI, use a video-to-video edit that names the style and what to keep, or restyle one frame and animate it.
Day to night video with AI: edit, generate, or grade
Turn a day video into night with a video-to-video AI edit, generate a day-to-night clip from two stills, or darken it with a color grade.
How to make AI videos from text or a photo
To make an AI video, pick what it starts from, describe the shot, set its length and shape, then generate and review. How to do each step on Sume.
How to write a prompt for an AI video generator
Write an AI video prompt as one shot: subject and action, camera, light, and framing. A template, worked examples, and what goes in settings instead.
Image to video prompt examples: what to write
An image-to-video prompt needn't describe the photo again. It says what moves, what the camera does, and what stays still. Examples by photo type.
Camera movement prompts for AI video: pan, dolly, orbit
Name the camera move in the prompt, one per shot, with its direction and speed; Sume's video API has no camera setting. Terms, examples, and limits.
AI cartoon video generator from text: how to set the style
Name the cartoon or anime look in your prompt, or draw a styled still first and animate it as the first frame. Sume's video API has no style field.
AI video transition generator: bridge one shot to the next
An AI transition is a generated clip that starts on the last frame of one shot and ends on the first frame of the next. How to make one with Sume.
AI video with multiple characters: get everyone in one shot
Give the model every character: one still with the whole cast as the first frame, or one reference image per character on a model that takes several.
Text to speech in Korean: send Hangul text with language ko
For Korean text to speech, send the script in Hangul with the language set to ko. How Sume's TTS API reads Korean, checks the voice, and bills it.
Multilingual text to speech API: one request per language
Make speech in several languages by sending one TTS request per language, each with the translated script and its language code. How Sume handles it.
AI voiceover with my own voice: clone once, reuse in TTS
Make an AI voiceover in your own voice: clone it once from a short clip in Sume's Voices library, then use its id as the voice for text to speech.
AI voice generator with a prompt: describe the speaker
An AI voice generator with a prompt designs a new voice from a written description. In Sume, describe a person in Assets → Voices, then use it in TTS.
AI music prompt examples: a template plus 6 briefs
A good AI music prompt reads like a brief: mood, genre, BPM, key, instruments, one moment, and era. Here is a template and six examples to adapt.
Image to music AI: generate a track from a photo
Image to music AI uses a picture as an input for a track. On Sume, send image_url with the text prompt to the Music Router; the price stays the same.
How to combine two photos into one with AI
Yes, AI can combine two photos into one: send both as references to an image model and describe the single scene you want. How to do it with Sume.
How to generate variations of an image with AI
Send the image as a reference, say what may change and what must stay, and set n for several results per call. How to do it on Sume's Image API.
Photo to painting AI: turn a photo into a painting
Turn a photo into a painting with AI: send it as a reference image, name the style in the prompt, and keep its shape with aspect_ratio auto.
Sketch to image AI: turn a drawing into a finished picture
Turn a sketch into an image with AI: send the drawing as a reference, describe the finished result, and ask for up to four versions per call.
Consistent character AI image generator: reuse one reference
Keep one character consistent across AI images: send the same reference image with every request, repeat its description, and change only the scene.
AI image seed: what it is and how to repeat an image
An AI image seed fixes a generation's random start so a result can repeat. Sume's image API does not serve seed yet; reuse a reference image instead.
AI image with text generator: get the words right
Make an AI image with text: quote the exact words in the prompt, raise the quality setting, proofread every letter, and set exact copy yourself.
Image to video vs reference to video: what's the difference?
Image-to-video makes your picture the first frame; reference-to-video uses pictures, clips, or audio as guidance. Which to use, and which one wins.
How to make a picture move with AI: pick the motion
Give the picture to an image-to-video model as its first frame and describe the motion. Motion control copies a dance; lip sync makes a face talk.
Seamless loop AI video: make a clip end where it starts
To loop an AI video, send one image as both its first and last frame, then compare the two ends before you loop it. Which models take an end frame.
What is an AI video seed? How to repeat a result without one
A seed fixes a generator's random starting point. Sume's video models take none and refuse the field. How to keep a clip or a look without one.
AI video negative prompt: how to keep things out of a clip
Sume's video API has no negative prompt field, and today sending one returns a 400. Describe the shot you want, then pin its frames, look, and sound.
AI video from multiple images: frames, references, stills
On Sume, one AI clip takes two images, as its first and last frames. For more, chain clips pair by pair, use references, or hold them as stills.
AI video 4K quality prompt: what actually sets resolution
Writing 4K in a prompt is not how Sume sets resolution. Request 4K in the resolution field of a model that lists it, or upscale a finished clip.
Seedance 2.5 API: 30-second clips, resolutions, references
Seedance 2.5 on Sume is seedance-2.5: 4–30 second clips at 480p, 720p, or 1080p. The documented limits, inputs, and billing for each Seedance id.
Sora API alternatives for video generation after the shutdown
The Sora API shut down on September 24, 2026. Compare Runway, Kling, fal, Replicate and Sume by models, audio, price unit, API shape and limits.
Image-to-video API: set the first and last frame with frame_images
Send frame_images to POST /v1/videos with a first_frame and an optional last_frame. Which Sume models take each frame, what wins, and what gets refused.
Reference-to-video API: guide a clip with images, video, and audio
Send input_references to POST /v1/videos to guide a clip with reference images, videos, or audio. Which Sume video models take each type, and how many.
AI video editing API: edit a video with a prompt (video-to-video)
Edit an existing clip with a prompt: send video_url to POST /v1/video-router/generate with gemini-omni-flash-1.1. What edit mode takes, rejects, and costs.
GPT Image 2.5 API on Sume: quality, sizes, masks, and references
Call ChatGPT Image 2.5 through Sume's POST /v1/images: pick a quality tier up to max, set custom pixel sizes, add a mask, and send up to 16 reference images.
Text-to-video API with audio: which video models generate sound
On Sume, POST /v1/videos makes sound on models whose catalog sets generate_audio. Which models make audio always, optionally, or never, and what is refused.
AI video generation API length limits: up to 30 seconds per clip
On Sume, seedance-2.5 (4–30 s) and wan-3.0 (2–30 s) make 30-second clips; other models stop at 15 s or less. Limits by model, the error, and going longer.
Vertical 9:16 video generation API: aspect ratios by model
For vertical video, send aspect_ratio "9:16" to POST /v1/videos. Which Sume models support 9:16, 1:1, and 21:9, and why a pixel size returns 400.
4K AI video generation API: resolutions by model, 360p to 4K
For 4K on Sume, pin gemini-omni-flash-1.1 with resolution 4K; minimax-h3 upscales to 2K or 4K. Resolutions for every video model, and the price effect.
Gemini Omni Flash 1.1 API: text, image, and reference video modes
Call Gemini Omni Flash 1.1 on Sume as gemini-omni-flash-1.1: text, image, or reference to video, 3–10 second clips from 360p to 4K, with native audio.
MiniMax H3 API: H3 and H3 Max video at native 768p with stereo audio
Call MiniMax H3 and H3 Max on Sume as minimax-h3 and minimax-h3-max: 5–15 second clips at native 480p or 768p, 1080p on H3 Max, always with stereo audio.
Nano Banana Pro API on Sume: 4K tiers, aspect ratios, and edits
Call Nano Banana Pro or Nano Banana 2 through Sume's POST /v1/images: pick a 512 to 4K resolution tier, a native aspect ratio, and up to 10 reference images.
Lip sync API: turn an image and audio into a talking clip
Send a still image and Sume-hosted audio to VEED Fabric 1.0 or MiniMax H3 Max Lip Sync and get a talking clip back. Inputs, limits, and per-second pricing.
Image generation API models on Sume: edits, references, and masks
Sume's image generation API lists 17 models. See which edit from reference images, how many references each takes, which are text-only, and which take masks.
AI image generation API aspect ratios: 4:5, custom sizes, and auto
Send aspect_ratio or image_size to Sume's POST /v1/images: which image models accept 4:5, which take custom pixel sizes, and when to send auto on edits.
Wan 3.0 API: 2–30 second AI video with audio, frames, and references
Call Wan 3.0 on Sume as wan-3.0: 2–30 second clips at 480p, 720p, or 1080p from a prompt, first and last frames, or image, video, and audio references.
Seedream 4.5 API on Sume: image edits, custom sizes, and 5 Lite
Call Seedream 4.5, Seedream 5.0 Lite, or Seedream 4.0 through Sume's POST /v1/images: edit from up to 10 reference images and set custom pixel sizes.
4K AI image generation API: resolution, quality, and image count
Only Nano Banana 2 and Pro list a 4K tier on Sume's POST /v1/images. See each model's resolution tiers, quality levels, per-call image count, and formats.
What AI models does Sume support? Every model id, by API surface
Sume supports 11 video models, 17 image models, Music and TTS Router ids, Avatar 1.0, and lip-sync models. Every id, grouped by endpoint.
Motion control API: animate an image with a driving video
Kling 3.0 Motion Control on Sume animates a still image with the motion of a driving video up to 30 seconds long. Request fields, limits, and price.
Text to speech API: generate speech in an avatar's voice
Sume's text to speech API, POST /v1/tts-1.0/generate, speaks up to 20,000 characters in a ready avatar's voice, with word timestamps and sentence audio slices.
Consistent character across multiple AI video shots: 3 API inputs
Three documented Sume API inputs send the same character source into every shot: a reusable Avatar 1.0 avatar, one first-frame still, or image references.
Music generation API: the Sume Music Router with Lyria 3.5
Sume's Music Router turns a text prompt into a track via POST /v1/music-router/generate. sume/music-auto picks the engine, Lyria 3.5 today.
Image generation API with reference images: POST /v1/images
Send a prompt plus public HTTPS reference images to Sume's POST /v1/images. Pin a catalog model or send sume/auto; the catalog lists each model's limits.
TikTok trending video search API: ranked metadata for research
Sume's POST /v1/trending-videos/search returns ranked public TikTok video metadata for a brand, product, creator, or keyword. It does not download videos.
Video 1.0 and Image 1.0 are retiring soon: move to sume/auto
Sume Video 1.0 and Image 1.0 are retiring soon and already run as aliases for the Auto path. New integrations call /v1/videos or /v1/images with sume/auto.
An OpenRouter-compatible video API: sume/auto or a pinned model
Sume's POST /v1/videos follows OpenRouter's video generation API field for field. Let sume/auto pick the model, or pin a catalog id like seedance-2.5.