Guides
Sume guides: the API, Formats, agents, models, media tools and pricing, each answer dated and sourced.
Amazon Brand Story card specs: 362x453 image, 166x182 ASIN tile
Brand Story's media asset card needs 362x453 or larger and the four-ASIN card 166x182. Which Sume canvases clear its 16-pixel and pixel-floor rules.
Amazon A+ four-column images: 300x225 minimum, made as 4:3
Amazon's Premium four-column A+ module needs images of at least 300w x 225h. Make them as 4:3 stills at 1024x768, which clears Sume's pixel floor.
Amazon Premium A+ full background image: ask for 1472x608
Amazon needs a desktop image of at least 1464x600, and 1464x600 is not a multiple of 16. Request 1472x608 on openai/gpt-image-2.5 and a 960x720 mobile image.
Amazon Premium A+ hero video: 960x540 video, 1464x600 preview
Amazon's Premium Hero Video module wants a video of at least 960x540 and a preview image of at least 1464x600. Plan a 16:9 clip and a separate still.
Amazon A+ regimen carousel: step images for a routine or gift set
The Premium regimen carousel holds 2 to 5 step panels with tabs. Plan one image per step, desktop and mobile, and the Sume Format for usage footage.
Anam 99.9% uptime SLA vs Sume failed-job retry metadata and refunds
Anam states a 99.9% uptime SLA for Cara-4. Sume documents what a failed avatar job exposes, category and retryability, and refunds the reservation.
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.
Anam custom avatar slots per plan vs Sume avatar handles
Anam limits active custom avatars by plan, from 1 on Free to 10 on Professional. Sume's avatar docs describe a handle per avatar and one avatar per video.
Anam per-second billing and spend cap vs Sume reserve at submit
Anam bills live sessions by the second against a spend cap. Sume reserves the estimated USD at submit, captures it on success and refunds it on failure.
Anam session limit per plan vs Sume's 4-60 second window
Anam caps one live session by plan, from 3 minutes on Free to 2 hours on Growth. Sume limits each avatar request to a 4-60 second estimated script.
AssemblyAI disfluencies: true (English only) vs Sume STT words[]
AssemblyAI's disfluencies: true raised filler-word recall from 49.7% to 76.3%, English only. Sume STT has no such flag, so check words[] on your clip.
AssemblyAI format_text false: 'one hundred' vs 100 and Sume STT
AssemblyAI's format_text: false returns spoken form, 'one hundred' not 100. Sume STT has no formatting toggle; its request is a closed schema.
AssemblyAI speech models: unpinned routing and Sume's fixed STT id
AssemblyAI will route unpinned async requests to Universal-3.5 Pro; pin speech_models to stay put. What changes, and why Sume STT has no model to pin.
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.
AssemblyAI Universal-3.5 Pro and Urdu: language_code on Sume STT
AssemblyAI fixed a bug that sent Urdu to Universal-3.5 Pro, which covers 18 languages. How a language hint behaves on Sume STT, and what to check.
TTS per sentence, then concat: join up to 20 clips in one file
Generate TTS one sentence at a time, then join up to 20 clips with Sume timeline audio concat: sample-domain, no re-synthesis, $0.01 flat per job.
Caption animation speed in and out: Sume motion overrides
Tune burned-in caption animation with design.motion: enter_seconds, exit_seconds, emphasis_in_seconds and emphasis_out_seconds, set per caption request.
Subtitles: how many words per line with design.phrasing
Sume video captions let design.phrasing set max_words (1-12), max_chars (4-60) and pause_seconds (0.05-3) per phrase. Not supported on punch or tiktok-green.
Subtitle position on video: Sume anchor_ratio for captions
Move burned-in captions up or down with design.placement.anchor_ratio, and set a separate landscape_anchor_ratio. A fraction of frame height, per request.
Editorial two-line video captions: the editorial-emphasis style
Sume's editorial-emphasis caption style is a left-aligned two-line card where the phrase-final word drops to a second line at about twice the size.
Captions app 10-minute captions vs Sume's 60-second inline cap
Captions processes videos up to 10 minutes. Sume's inline avatar captions reject estimates above 60 seconds; standalone video-captions is a separate job.
Captions AI Twin from a video upload vs Sume's photo avatar
Captions can build an AI Twin from an uploaded video. Sume's avatar API takes a prompt, a profile or a public HTTPS reference image, but no video input.
Captions Avatar Looks in Prompt to Video: the Sume handle workflow
Captions saves looks inside one avatar for Prompt to Video. For several looks in Sume, make one avatar_handle per look and render one job per final video.
Captions horizontal 16:9 AI Edit vs Sume avatar aspect ratios
Captions AI Edit now outputs 16:9. Sume avatar videos accept 16:9 too, at 720p only, with a script or plan estimated at 4-60 seconds. 9:16 is the default.
Captions app SRT export vs Sume burned-in caption cues
The Captions app can export an SRT file for external caption tracks. Sume burns captions into the MP4 from authored cues with text, start and end.
Cartesia normalization: auto, off or a locale code, versus Sume text
Cartesia Sonic 3.6 adds a normalization field set to auto, off or a locale code. Sume TTS has no such field, so write dates and numbers out in the transcript.
Cartesia Sonic 3.6 heteronyms: read, bass, live, and Sume pricing
Sonic 3.6 improves English heteronyms like read, bass and live in context. When context is enough, when to use a dictionary id, and Sume's TTS rate.
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.
Claude Code 2.1.286 MCP Bearer redaction: Sume key cleanup
Claude Code 2.1.286 stopped MCP errors from printing a credential after Bearer. Update, then sweep old logs and rotate any Sume key that appeared there.
Codex MCP OAuth 503 on discovery: check Sume's two URLs
Codex 0.156.0 refreshes MCP credentials after an OAuth discovery 503. To see if it came from Sume, curl its two well-known metadata URLs.
ComfyUI ID-V2V vs reference video and face swap on Sume
ComfyUI v0.38.1 adds ID-V2V for Wan 2.1 and VACE models. On Sume, keep identity with video references on models that list them, or use Beta face swap.
Flux TTS CONTROL_COMBINATION_INVALID and the 1.15 pause speed cap
Deepgram Flux TTS rejects some control combinations and caps speed at 1.15 with a pause. The error codes, the rules, and Sume's 0.6 to 1.5 speed range.
Deepgram Flux TTS inline IPA vs Sume's pronunciation dictionary id
Deepgram Flux TTS now takes inline IPA overrides in Early Access. Sume TTS takes a pronunciation_dict_id instead. How the two approaches differ in practice.
Flux TTS pause markers: 8 per request, 500-3000 ms, and Sume scripts
Flux TTS allows up to 8 pause markers of 500 to 3000 ms per request, batch only. Plan a script around that limit and see what Sume gives you for pacing.
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.
Deepgram self-hosted 261001 drops Whisper: what Sume STT callers do
Deepgram Self-Hosted release 261001 removes Whisper support and asks you to move to Nova-3 first. What it means for Sume STT, which has no model to migrate.
Extract audio from MP4 to WAV or MP3: the detach defaults
Sume audio detach returns WAV (pcm_s16le, sample-exact) by default or MP3 at 128 kbps. Pick WAV for speech-to-text and timeline use, MP3 when file size matters.
Extract audio segment start beyond video length: error and fix
Audio detach fails detach_start_past_source when range.start is past the probed duration. It differs from audio_detach_range_empty. Check duration first.
ElevenLabs Flows API states vs Sume job status and webhooks
ElevenLabs Flows generations report pending, generating, completed and failed. Sume jobs use async, a 30-second wait cap and terminal-only webhook events.
ElevenLabs MCP server is now hosted: what Sume's MCP offers
ElevenLabs deprecated its local MCP server for a hosted one with OAuth. Sume's hosted MCP at mcp.sume.com/mcp has music, TTS and STT tools. Setup compared.
ElevenLabs Music v2.5 plan limits vs Sume's 5000-character prompt
ElevenLabs Music v2.5 plan chunks reach 6,132 characters, up to 30 lines of 200. Sume Music takes one 5000-character prompt and rejects duration fields.
EU AI icon alt text and ARIA label for AI-generated video
The Commission says the EU AI icon should, if possible, be readable by assistive technology via alt text or ARIA labels. Burned-in pixels need text in the page.
EU AI icon: black, white or 50% transparency on video?
The EU AI icon has four variations. Pick the one that stays clearly perceivable on your footage; test each on a bright and a dark scene with Timeline compose.
EU AI icon for fully AI-composed music: generated tracks
The EU icons page lists fully AI-composed music or art under the Fully AI-Generated icon, with limited disclosure for artistic works. Handling a Sume track.
fal queue retries up to 10 times: who counts attempts on Sume
fal retries failed queue requests on new runners, up to 10 attempts. Sume's docs put retries with the caller, guarded by an Idempotency-Key.