Synthesia Roleplay Sessions vs Sume scripted scenario clips
Synthesia launched Roleplay and Survey Sessions on Oct 1. Sume has no live roleplay, but can render the scenario prompt as a short avatar clip.
Sume has no live roleplay avatar. It can render the customer or manager lines of a training scenario as avatar clips of 4 to 60 seconds. Synthesia's Sessions page, read 2026-10-01, lists Roleplay and Survey Sessions as live.
What can I render?
Each scenario line becomes one POST /v1/avatar-1.0/talking-video job with a script. One avatar speaks per final video, and silence beats are available with voice.type silence. Aspect ratios include 16:9 and 9:16.
| Item | Sume avatar clip |
|---|---|
| Endpoint | POST /v1/avatar-1.0/talking-video |
| Clip length | 4 to 60 seconds |
| Speakers per final video | One avatar |
| Silence beats | voice.type silence |
| Aspect ratios | Include 16:9 and 9:16 |
How does a learner respond?
Your app plays a clip, records the learner and sends the audio to Sume speech-to-text. The branching and feedback are your code. Sume does not score the answer.
Which should I pick?
Pick Synthesia Sessions for a live back-and-forth. Pick Sume when you want pre-rendered scenarios you can store, version and ship in your own LMS.
Sources
Related posts
More in Sume Avatar 1.0
- Synthesia Survey Sessions vs Sume: not interactive, but scripted
Synthesia's Survey Sessions avatar asks questions live and reports themes. Sume renders avatar question clips from a script, with no live conversation.
- VEED Fabric Emotions audio tags vs Sume Fabric audio_url
VEED's Fabric Emotions adds inline tags like [excited] in the script. On Sume, Fabric takes a finished audio_url; emotion lives in the TTS step.
- Introducing Sume Avatar 1.0
Sume Avatar 1.0 is a multi-agent orchestration system as a single avatar model.
- Avatar Face Swap API (Beta): apply an avatar face to a video
Avatar Face Swap 1.0 is a Beta Sume endpoint that applies a ready avatar's face to a short public source video. Required fields, limits, and polling.
Written by Sume