Synthesia Assistant styles vs Sume's scene prompt and previews
Synthesia Assistant asks for a Cinematic or Presentation delivery style before scenes generate. Sume uses scene direction plus first-frame previews instead.
Synthesia Assistant makes you choose a delivery style, Cinematic or Presentation, before a single scene is generated. Sume has no delivery-style switch. You steer the look with scene direction (a prompt or a photo) on Avatar Video, and you can approve first-frame stills before the full render starts.
Assistant facts are from Synthesia's launch post. Sume facts are from Generate avatar video and Avatar video previews, read 2026-10-01.
How does Assistant plan a video?
The post says you describe the video with a prompt, files or URLs, then align on structure, tone and scene count in a back-and-forth chat. Only then do you pick Cinematic or Presentation, before scenes are generated.
What does Sume use for direction?
Scene direction is a field, not a chat. Use scene: { "type": "prompt", "prompt": "..." } or a photo scene with a public HTTPS image_url. For several beats, send ordered video_inputs, built for hooks, demos or silence beats in one composed video.
| Assistant step | Sume equivalent |
|---|---|
| Scene count | Length of video_inputs |
| Tone and look | scene prompt or photo; scene background |
| Review before build | POST /v1/avatar-video-previews first-frame stills |
| Delivery style | No such field in the docs |
How do I review before the full render?
Create an avatar video preview, regenerate stills if needed, then call generate-video on the preview id. Previews stop at the first-frame still, and preview stills are tier-independent: quality only changes the final video tier. Inline captions on a preview are stored for generate-video, not burned into stills.
What stays the same?
The 4 to 60 second window applies to previews too. See the related first-frame preview comparison.
Sources
Related posts
More in Use cases
- Synthesia Avatar Builder credits: 14 per option, and Sume jobs
Synthesia Avatar Builder charges 14 credits per generated option. Sume creates an avatar with one job per request via POST /v1/avatar-1.0/generate.
- Synthesia brand kit fonts vs Sume caption fonts: Hangul only
Synthesia Motion Graphics now use brand kit fonts. Sume's caption font field takes a Hangul face only, so Latin brand fonts cannot be set there.
- Synthesia bulk download of 20 videos vs Sume result URLs
Synthesia can bulk download up to 20 videos as .mp4 files. On Sume you list avatar-video resources and fetch each job's result for its media.sume.com URL.
- Synthesia CSV bulk personalization vs Sume bulk runs (1-100)
Synthesia maps CSV or XLSX columns to template variables. Sume bulk runs take a JSON array of 1 to 100 Format runs with a concurrency window of 1 to 16.
Written by Sume