Guides
Sume guides: the API, Formats, agents, models, media tools and pricing, each answer dated and sourced.
How long does Sume retry a webhook before giving up?
Sume job webhooks give up after about 4.5 minutes of gaps, run webhooks after about 3 hours. Cumulative timings per attempt, then redeliver or poll.
Rotating a webhook secret during a gradual deployment
Sume signs with both the new and old secret for 24 hours after rotation, so two receiver versions can run side by side. Upgrade the verifier first, then rotate.
Can an AI agent debug a failed webhook on Sume over MCP?
Over MCP an agent can read job status, events and delivery status to see why a webhook did not arrive. Redeliver is a REST call that needs jobs:write.
Webhook signature mismatch: compare the secret fingerprint
Before filing a ticket for a Sume signature mismatch, compare the secret fingerprint header with the dashboard value. It is safe to paste into a ticket.
HeyGen look packs vs Sume: a new avatar per look
HeyGen's POST /v3/avatars/looks adds looks to an avatar. Sume has no look-pack endpoint: make one avatar per look and steer the scene with a prompt.
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 Video Agent edit_plan vs Sume preview regenerate
HeyGen's edit_plan revises named scenes in one turn, up to 50 items. Sume has no in-place scene edit: regenerate preview stills, then render.
HeyGen API concurrency limit: 1.5x burst vs Sume queued jobs
HeyGen Enterprise burst adds up to 50 slots billed at 1.5x. Sume queues jobs above plan concurrency and returns 429 only when the queue is full.
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.
HeyGen avatar voice id: default_voice_id vs Sume avatar_handle
HeyGen's PATCH /v3/avatars/{group_id} stores a default_voice_id. On Sume, TTS can take an avatar_handle and resolve that avatar's ready voice.
HeyGen voice clone API: 20+ minutes, paid slot, no Sume clone
HeyGen's professional voice clone needs 1-10 recordings totaling 20+ minutes and a paid slot. Sume's TTS tool selects voices and has no clone upload.
HeyGen translation SRT captions vs Sume burned-in captions
HeyGen now generates caption sidecars for every translation and lipsync job. Sume burns captions into the video and does not accept SRT as input.
HeyGen API idempotency key vs Sume: two different 409s
HeyGen returns 409 request_in_progress for an in-flight retry. Sume returns 409 idempotency_conflict only when a key is reused for a different payload.
HeyGen video scenes API vs Sume job result previews
HeyGen's GET /v3/videos/{video_id}/scenes returns each scene's visuals and script. Sume job results return media.sume.com artifacts and scene previews.
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.
AI avatar in Microsoft Teams: Tavus PAL joins, Sume makes clips
Tavus PALs can join Microsoft Teams calls by invite address or Teams URL. Sume renders 4-60 second 16:9 avatar clips you share into a meeting.
Hedra MCP for Claude, and how Sume's hosted MCP connects
Hedra's MCP and CLI let Claude and other agents generate images, video and audio. Sume's hosted MCP lives at mcp.sume.com/mcp with write and paid gates.
Hedra API pricing: estimate endpoint vs Sume dry_run
Hedra says you can price the exact request with an estimate endpoint. Sume's hosted MCP has dry_run and max_spend_usd gates that preview cost before a job.
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.
Smooth jump cuts: trim, then a short fade between clips
Descript added Smooth all for jump cuts. Via API, trim the clean segments and join them in Timeline 1.0 with a fade of up to 1 second. No AI regeneration.
Descript jump cut smoothing cost vs Sume flat edit rates
Descript prices smoothing at 0.5 AI credits per second of audio and 1.0 per second of video. Sume's edit steps are flat per job or per output minute.
Replace video audio with an AI voice (and the lip-sync catch)
Sume has no one-call audio swap: detach the audio, transcribe it, make a new voice with TTS, and lay it on a Timeline. Lips will not re-sync to the new voice.
AI music for one section of a video: no duration field
Sume's Music 1.0 rejects duration and duration_seconds. Ask for the length in the prompt, then loop and fade the track to fit one section on a Timeline.
Change caption style without transcribing again: source_caption_id
Pass source_caption_id instead of video_url to re-burn a clip under a new style. Sume reuses the stored word timings, so speech-to-text runs only once.
caption_hangul_text_latin_style: the 400 and the fix
Sume returns 400 caption_hangul_text_latin_style when Korean copy is sent to slam, punch or tiktok-green. Name a Hangul style such as black-outline instead.
caption_font_requires_hangul_style: why font returns 400
Sume's font field on video captions is Hangul-only: sending it with slam, punch or tiktok-green returns 400 caption_font_requires_hangul_style.
Customize caption colors via API: not on punch or tiktok-green
Sume's design overrides change caption colours, weight, placement and motion per request, but punch and tiktok-green ignore them. Which styles accept design.
caption_no_speech: caption a silent clip with cues
caption_no_speech means the clip has no audible speech. Sume's fix is next_action use_overlay_captions: send cues with text, start and end and skip ASR.
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.
Remove background from video with AI: what Sume covers
Sume has no video background-removal endpoint: RMBG 1.0 takes a still image. What you can do instead is a prompt edit with video_to_video, or a crop.
WAV 16-bit PCM vs 32-bit float: what audio detach returns
Sume audio detach writes wav as 16-bit PCM (pcm_s16le) by default. If your camera records 32-bit float, here is what that means and which options you get.
Use a frame from your footage as a reference for AI video
Pull a still at a time you pick with video frames (unbilled), then pass it as image_url or reference_image_urls to a Sume video model. Steps and limits.
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.
YouTube A/B testing video cuts: build hook variants by API
Build three hook variants of one video as separate files: trim for the hook, Timeline to join hook and body, and a fresh Idempotency-Key per request.
YouTube dynamic thumbnails: generate three options by API
Dynamic thumbnails need three candidate files. Send three Sume image jobs in webhook mode, each with its own Idempotency-Key, and collect the files when done.
Beat sync video editor via API: plan cuts from a stated BPM
Sume has no beat-detection tool. You can ask Music 1.0 for a BPM, then set Timeline 1.0 slot starts and durations as multiples of one beat.
CapCut Codex plugin plus Sume hosted MCP in one session
CapCut's Codex plugin drafts and edits in chat; Sume's hosted MCP at mcp.sume.com generates media. Here is what each does and how files pass between them.
EU AI icon on video: keep burned captions off the label
The EC says the AI icon should sit where no overlay elements exist. Burn captions first, then compose the icon on top in a different band.
How big should the EU AI icon be on a video? No number given
The EC only says clearly visible size and gives no pixels. With Sume Timeline compose, width_ratio sets the badge width as a share of frame width.
Can ChatGPT make videos from photos? Image to video now
Not with Sora, which OpenAI discontinued. ChatGPT can send a photo's public URL to an image-to-video tool over MCP and get a clip back.
Can ChatGPT make videos with sound? Audio and voice
Yes, through a video tool whose model generates audio. A voice that speaks your script is a second step: text to speech, then lip sync.
Can ChatGPT make long videos? Clip limits and how to join
Not in one clip: generated clips top out at 15 or 30 seconds. ChatGPT can join many clips over one audio track into a render of up to 30 minutes.
Can ChatGPT make videos better quality? Upscaling a clip
With an upscaling tool, yes: ChatGPT can send a clip's public URL to a video upscaler over MCP. For new clips, ask for a higher resolution.
Can ChatGPT make slideshow videos? Stills, voice, one MP4
Yes, through tools: ChatGPT can make the slides, voice the script, and have a timeline tool hold each still for its line in one MP4.
Can ChatGPT make TikTok videos? Vertical clips and limits
ChatGPT can write the hook and, with a video tool over MCP, have a 9:16 clip rendered. Posting it to TikTok is a separate step you do.