Sync React-1

POST/v1/run

Lipsync React 1 is Sync Labs's video-to-video AI model. Transform, enhance, and edit video content using text prompts - from style changes to object manipulation and scene modification.

Request body

Submit an async generation request. The model field selects the model; other fields are model-specific input parameters.

stringmodelrequired

Model identifier. Set to sync/lipsync/react-1.

Default: sync/lipsync/react-1

Optional<string>video

URL to the input video. Must be **15 seconds or shorter**.

Optional<string>audio

URL to the input audio. Must be **15 seconds or shorter**.

Optional<string>model_mode

Controls 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.

Allowed values: lips, face, head

Default: face

Optional<string>lipsync_mode

Lipsync mode when audio and video durations are out of sync.

Allowed values: cut_off, loop, bounce, silence, remap

Default: bounce

Optional<number>temperature

Controls the expresiveness of the lipsync.

Range: 0 to 1

Default: 0.5

Optional<string>emotion

Emotion prompt for the generation. Currently supports single-word emotions only.

Allowed values: happy, angry, sad, neutral, disgusted, surprised

Response Schema

The submit endpoint returns an accepted generation task. Poll the result endpoint with the returned id for terminal outputs or errors.

Optional<string>error

Error message if the task failed. Empty on success.

stringidrequired

Unique identifier for the generation task.

Optional<string>model

Model ID used for the prediction.

Optional<array>outputs

Array of generated content. Empty when status is not completed.

stringstatusrequired

Status of the task: pending, running, completed, failed, or timeout.

Allowed values: pending, running, completed, failed, timeout

Model capabilities

array<string>capability_tagsrequired

Capabilities declared by the model registry.

Default: video-to-video

stringexecution_moderequired

Execution mode declared by the model registry.

Default: async

# 1. Submit a generation request
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "sync/lipsync/react-1",
  "video": "https://static.sandbase.ai/examples/sync/lipsync/react-1/input_video_0.mp4",
  "audio": "https://static.sandbase.ai/examples/sync/lipsync/react-1/input_audio_1.mp3"
}'

# 2. If the response is still running, poll the returned id
curl https://api.sandbase.ai/v1/run/run_abc123 \
  -H "Authorization: Bearer $SANDBASE_API_KEY"

Response202 Accepted

{
  "id": "run_abc123",
  "model": "sync/lipsync/react-1",
  "status": "running",
  "outputs": []
}