HeyGen studio video scene limit: 50 scenes, and Sume's 4-60 s plan
HeyGen studio videos allow 50 scenes and 30 minutes per scene. Sume multi-scene video_inputs share one 4-60 second window and one resolved avatar.
HeyGen studio videos take 1 to 50 scenes, each up to 30 minutes. Sume's multi-scene Avatar Video uses ordered video_inputs, and the total planned duration must land in the 4-60 second window, with one resolved avatar per final video.
HeyGen details are from its Studio videos and Usage Limits pages; Sume details from Avatar videos, read 2026-10-01.
What are HeyGen's studio video limits?
A studio video is created with "type": "studio" on POST /v3/videos. The request's scenes array takes 1 to 50 whole-frame scenes of type avatar_video, image or video, concatenated in order. Each scene renders up to 30 minutes, and a scene over the cap fails during rendering.
Output settings such as aspect ratio, resolution and captions are global, set once per request.
How does Sume describe multi-scene video?
Use ordered video_inputs instead of a single script when you need scene hooks, demos or silence beats in one composed video. Total planned duration must still land in the 4-60 second window. Provide exactly one of script or video_inputs.
A silence beat uses voice.type: "silence" with a required duration.
How do the two compare side by side?
Same idea, very different ceilings.
| Limit | HeyGen studio | Sume Avatar Video |
|---|---|---|
| Scenes in one request | 1 to 50 | Ordered video_inputs, no scene count given in the docs read |
| Duration | 30 minutes per scene | 4-60 seconds total |
| Avatars per video | Per scene | One resolved avatar per final video |
| Backgrounds | Per scene | Expected to resolve to one shared scene |
Do I get a preview per scene on Sume?
Yes, when available. The previews docs list scene_previews[], one still per input scene, plus preview_image_url as the primary still. See the HeyGen composition endpoint compared with Sume previews.
What if I need more than 60 seconds?
Split the plan into several jobs, as the docs advise, and join the clips afterwards. Avatar video longer than 60 seconds covers that route.
Sources
Related posts
More in Developers
- HeyGen stale_edit_version 409 vs Sume idempotency_conflict
HeyGen returns 409 stale_edit_version when a template edit is out of date. Sume's 409 is idempotency_conflict: one key reused on a different payload.
- Hookdeck passes gzip bytes unchanged: verify Sume on raw bytes
Hookdeck now forwards binary and gzip bodies byte for byte. Read the raw bytes before parsing and verify the Sume sume-v1 signature over them.
- Hume Octave 2 description field vs Sume TTS emotion controls
Hume lists a voice description field; acting instructions are coming soon. Sume TTS 1.0 has generation_config: emotion text, speed 0.6 to 1.5, volume 0.5 to 2.
- Hume Octave takes 5,000 characters per utterance in MP3, WAV or PCM
Hume's TTS overview lists 5,000 characters per utterance and MP3, WAV or PCM output. Sume TTS 1.0 takes 20,000 characters and mp3, wav or raw containers.
Written by Sume