Models & Inputs
Video lip-sync
Lip-sync models that align an uploaded source video to uploaded audio.
POST /api/v1/processes with "type": "video-lipsync". Pick any model — the API does not plan-gate models. GET /api/v1/models returns the same capabilities at runtime.
Training behavior
maxis a trained model. A Max request withouttrainingIdtrains on the source video before generating, so the first run takes longer. Poll the process; once itstrainingIdappears, save it and pass it to later Max requests for the same trained source to skip training and start faster.lipdub-v2,pro, andsync-lipsync-v3are single-shot models. They generate directly from the supplied video and audio, require no training, and should not receivetrainingId. For alipdub-v2source video longer than the safe 59-second cap, Yapper creates or reuses a cached variant containing its first 59 seconds.
Input fields
| Field | Type | Required | Description |
|---|---|---|---|
sourceVideoAssetId | string | yes | Team video asset id from /assets, /assets/import, or the direct-upload flow. |
audioAssetId | string | yes | Team audio asset id from /assets, /assets/import, /assets/uploads, or /audio/speech. Its measured duration determines the exact quote and charge. |
trainingId | string | no | Sync-Max only. Reuse training from an earlier Max process; omit on the first Max run to train from the source video. Do not send for lipdub-v2, pro, or sync-lipsync-v3. |
disableAutoRetries | boolean | no | Disable automatic same-model retries. Defaults to false, so automatic retries are enabled. |
endTimeSeconds | number | no | Optional source-video trim end in seconds. Omit to use the full remaining clip. |
startTimeSeconds | number | no | Optional source-video trim start in seconds. Omit to use the beginning. |
Example
Add "dryRun": true to get the exact credit cost without starting, and always send an Idempotency-Key header on real starts.
POST /api/v1/processes
{
"type": "video-lipsync",
"model": "sync-lipsync-v3",
"input": {
"sourceVideoAssetId": "video_asset_id",
"audioAssetId": "audio_asset_id"
}
}Models
Cost depends on the input — use dryRun: true for an exact quote.
| Model | Name | Description |
|---|---|---|
lipdub-v2 | LipDub v2 | Single-shot LipDub model with direct video and audio ingestion. No training is required; longer source videos automatically use a cached 59-second safety-capped variant. |
max | Sync-Max | Train-once model for highest quality. The first run trains on the source video; reuse its trainingId for faster later runs. |
pro | Sync-Pro | Single-shot model with no training required. Quicker, with some artifacts on harder videos. |
sync-lipsync-v3 | Sync-v3 | Single-shot model with no training required, stronger alignment, and more natural motion. |