## Generate lip sync from uploaded media

`lipsync.generate_with_media(LipsyncGenerateWithMediaParams**kwargs)  -> LipsyncGenerate`

**post** `/v1/lipsync/generate-with-media`

Starts a lip sync job by uploading one video file and one audio file as multipart form-data.

### Parameters

- `audio: FileTypes`

  Target audio file.

- `video: FileTypes`

  Source video file.

- `disable_active_speaker_detection: Optional[bool]`

  Disable active speaker detection and use max-face lipsync preprocessing.

- `model: Optional[Literal["lipsync-2"]]`

  Optional model selector.

  - `"lipsync-2"`

- `reference_id: Optional[str]`

  Optional client-provided identifier for later retrieval.

### Returns

- `class LipsyncGenerate: …`

  - `request_id: str`

    Identifier of the created lip sync request.

  - `status: Literal["success"]`

    Current state of the newly created request.

    - `"success"`

### Example

```python
import os
from chamelaion import Chamelaion

client = Chamelaion(
    api_key=os.environ.get("CHAMELAION_API_KEY"),  # This is the default and can be omitted
)
lipsync_generate = client.lipsync.generate_with_media(
    audio=b"(binary)",
    video=b"(binary)",
    disable_active_speaker_detection=False,
    model="lipsync-2",
    reference_id="upload-demo-01",
)
print(lipsync_generate.request_id)
```

#### Response

```json
{
  "status": "success",
  "request_id": "3b7df3e8-f578-44de-b4f5-5f58dd6b89e0"
}
```