HeyGen image to video from a photo API vs Sume image_url
HeyGen type image animates a PNG or JPEG with a script and voice_id, no avatar setup. Sume does it with image_url plus audio on the Fabric route.
On HeyGen, POST /v3/videos with type: "image" takes a PNG or JPEG of a person plus a script and voice_id, and the page says "no avatar setup needed". On Sume the same shortcut is the Fabric route: send a public HTTPS image_url with a Sume-hosted audio_url, and no avatar record is created.
What does HeyGen's image type need?
An image of a person, as a public URL or an uploaded asset, and a voice_id. The image object replaces avatar_id; type: "image" and type: "avatar" are mutually exclusive. The result is polled with GET /v3/videos/{video_id}. Read 2026-10-01.
What does the Sume equivalent need?
POST /v1/veed/fabric-1.0 takes exactly one visual source, either image_url or avatar_id/avatar_handle, plus audio_url and duration_seconds. The schema describes image_url as a public HTTPS still image for audio-driven image-to-video. resolution is 480p or 720p, default 720p. The models page advises using the generated, inspected posed still as image_url, and avatar_handle only when the user named that avatar.
Where do the two differ?
| Input | HeyGen type image | Sume Fabric |
|---|---|---|
| Image field | image (url or asset id) | image_url |
| Speech | script + voice_id | Sume-hosted audio_url |
| Avatar record | Not needed | Not needed with image_url |
| Output size | resolution such as 1080p | 480p or 720p |
When should I make a reusable avatar instead?
If you will reuse one face across many videos, create an avatar from a photo with input.type: "photo" on POST /v1/avatar-1.0/generate, then call it by avatar_handle. Creating it is a separate job, per the avatar docs. For a one-off clip, image_url is enough; see lip-sync with a photo and audio.
Sources
Related posts
More in Developers
- HeyGen insufficient_credit vs Sume insufficient_credits (402)
HeyGen returns code insufficient_credit with HTTP 402. Sume returns insufficient_credits, plural, also 402. Match on the exact string and the status.
- HeyGen create avatar from a text prompt API vs Sume
HeyGen POST /v3/avatars type prompt takes up to 1000 characters and an aspect_ratio. Sume creates a text-only avatar with a Prompt input on avatar-1.0/generate.
- HeyGen Stripe Projects API key vs how you get a Sume key
HeyGen lets an agent provision a key with stripe projects add heygen/api. Sume keys are created in the dashboard, workspace-scoped and shown once.
- 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.
Written by Sume