InfiniteTalk Video to Video

POST/v1/run

InfiniteTalk dubs an existing video: it re-animates lips, face and body to match new speech audio.

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 meigen/infinitetalk/video-to-video.

Default: meigen/infinitetalk/video-to-video

stringpromptrequired

Text prompt guiding the generation.

Optional<integer>seed

Random seed for reproducibility.

Range: 0 to 2147483647

stringaudiorequired

Input audio URL.

Optional<integer>num_frames

Maximum frames to generate (41–241, 25 fps); output also stops at the end of the audio.

Range: 41 to 241

Default: 145

Optional<string>resolution

Output resolution (720p costs 2x).

Allowed values: 480p, 720p

Default: 720p

stringvideorequired

Input video URL.

Response Schema

The submit endpoint returns a run response. If its status is pending or running, poll GET /v1/run/{id} with the returned opaque ID until it reaches a terminal state.

stringidrequired

Opaque SandBase run identifier. Use it exactly as returned; no prefix is guaranteed.

stringstatusrequired

Current public run status.

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

Optional<string>model

Public SandBase model name used for this run.

Optional<array<object>>outputs

Present only for completed runs. Each object is capability-specific; inspect the selected model schema for its fields.

Optional<object>error

Present only for failed or timeout runs. Contains a public error type and sanitized message.

Optional<string>error.type

Stable public error category.

Optional<string>error.message

Sanitized error message safe to show to clients.

Optional<object>usage

Usage details when available.

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": "meigen/infinitetalk/video-to-video",
  "audio": "https://v3.fal.media/files/penguin/PtiCYda53E9Dav25QmQYI_output.mp3",
  "video": "https://storage.googleapis.com/falserverless/model_tests/video_models/ref_video.mp4",
  "prompt": "A woman with colorful hair talking on a podcast."
}'

# 2. If the response is still running, poll the returned id
curl https://api.sandbase.ai/v1/run/f3d2e8a1-7c4b-4a12-9d2e-123456789abc \
  -H "Authorization: Bearer $SANDBASE_API_KEY"

Response202 Accepted

{
  "id": "f3d2e8a1-7c4b-4a12-9d2e-123456789abc",
  "model": "meigen/infinitetalk/video-to-video",
  "status": "running"
}