# LatentSync

> ByteDance's open-source lipsync — syncs a video's mouth movements to any audio track with latent diffusion. State-of-the-art open lipsync quality.

- **Provider**: replicate
- **Model ID**: bytedance/latentsync
- **Category**: lipsync_face_animation
- **Credits**: 220 per request
- **Pricing Type**: fixed

## API Endpoint

Base URL: https://api.core.today/v1

### Create Prediction
POST /predictions

### Get Status
GET /predictions/{job_id}

### Cancel
DELETE /predictions/{job_id}

## Authentication

Header: `X-API-Key: YOUR_API_KEY`

## Input Parameters

- `guidance_scale` (number, optional): Guidance scale (Default: `1`; Range: min: 0, max: 10)
- `seed` (integer, optional): Set to 0 for Random seed (Default: `0`)
- `audio` (string, optional): Input audio to 
- `video` (string, optional): Input video

## Example Request

```json
{
  "model": "bytedance/latentsync",
  "input": {
    "audio": "https://replicate.delivery/pbxt/MGZuENopzAwWcpFsZ7SwoZ7itP4gvqasswPeEJwbRHTxtkwF/demo2_audio.wav",
    "video": "https://replicate.delivery/pbxt/MGZuEgzJZh6avv1LDEMppJZXLP9avGXqRuH7iAb7MBAz0Wu4/demo2_video.mp4",
    "seed": 0,
    "guidance_scale": 1
  }
}
```

## Response Format

```json
{
  "job_id": "abc123",
  "status": "pending",
  "provider": "replicate",
  "model": "black-forest-labs/flux-schnell",
  "created_at": "2026-01-01T00:00:00Z",
  "result": null,
  "error": null
}
```

Status values: `pending`, `processing`, `completed`, `failed`, `cancelled`

## Usage Flow

1. POST /predictions with model and input → receive job_id
2. Poll GET /predictions/{job_id} until status is `completed` or `failed`
3. Result contains output URL(s) or data

## Output Type

url

## Tags

lipsync, video-editing, face-animation, bytedance, open-source

## Documentation

https://replicate.com/bytedance/latentsync