Sync Labs

This page is auto-generated from model configurations. Last updated: 2026-03-13.

This reference lists all available Sync Labs video generation models and their parameters. Use these parameter names when calling the Generation API.


Sync Lipsync React-1

Use React-1 from SyncLabs to refine human emotions and do realistic lip-sync without losing details!

Model ID: model_sync-lipsync-react-1

Capabilities: video2video

LLM Markdown: https://app.scenario.com/api/models/model_sync-lipsync-react-1/markdown

ParameterTypeRequiredDefaultMinMaxAllowed ValuesDescription
videofileYes----Input video file
audiofileYes----Input audio file. Maximum duration is 15 seconds.
emotionstringNoneutral--happy, angry, sad, neutral, disgusted, surprisedEmotion prompt for the generation.
modelModestringNoface--lips, face, headControls the edit region and movement scope for the model. Available options: "lips": Only lipsync using react-1 (minimal facial changes). "face": Lipsync + facial expressions without head movements. "head": Lipsync + facial expressions + natural talking head movements.
lipsyncModestringNobounce--loop, bounce, cut_off, silence, remapLipsync mode when audio and video durations are out of sync.
temperaturenumberNo0.501-How expressive lipsync can be (0-1)

Sync Lipsync v2

Model ID: model_sync-lipsync-v2

Capabilities: video2video

LLM Markdown: https://app.scenario.com/api/models/model_sync-lipsync-v2/markdown

ParameterTypeRequiredDefaultMinMaxAllowed ValuesDescription
videofileYes----Input video file
audiofileYes----Input audio file
syncModestringNoloop--loop, bounce, cut_off, silence, remapLipsync mode when audio and video durations are out of sync
temperaturenumberNo0.501-How expressive lipsync can be (0-1)

SYNC Lipsync v2 Pro

Model ID: model_sync-lipsync-v2-pro

Capabilities: video2video

LLM Markdown: https://app.scenario.com/api/models/model_sync-lipsync-v2-pro/markdown

ParameterTypeRequiredDefaultMinMaxAllowed ValuesDescription
videofileYes----Input video file
audiofileYes----Input audio file
syncModestringNoloop--loop, bounce, cut_off, silence, remapLipsync mode when audio and video durations are out of sync
temperaturenumberNo0.501-How expressive lipsync can be (0-1)
activeSpeakerbooleanNofalse---Whether to detect active speaker (i.e. whoever is speaking in the clip will be used for lipsync)