> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.empiriolabs.ai/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.empiriolabs.ai/_mcp/server.

# Pixverse Lip Sync

> Aligns mouth movement in an existing video to an uploaded audio track or to text spoken by one of fourteen built-in voices.

![Pixverse Lip Sync](https://media.empiriolabs.ai/model-logos/pixverse-lipsync.png)

[PixVerse](/providers/pixverse) · Video Generation

`POST /v1/videos/generations`

Aligns mouth movement in an existing video to an uploaded audio track or to text spoken by one of fourteen built-in voices.

## At a glance

| Field               | Value                            |
| ------------------- | -------------------------------- |
| Model id            | `pixverse-lipsync`               |
| Model release date  | 2025-07-14                       |
| Input modalities    | Text, Video, Audio               |
| Output modalities   | Video                            |
| Context window      | -                                |
| Weight precision    | -                                |
| Features            | lipsync, audio_in, video_editing |
| Native inference    | No                               |
| New                 | No                               |
| Supported endpoints | `POST /v1/videos/generations`    |
| Alternate model ids | `pixverse/lipsync`               |

## Pricing

| Charge | Spec       | Rate       |
| ------ | ---------- | ---------- |
| Speech | per second | \$0.020444 |

## Example request

```bash
curl https://api.empiriolabs.ai/v1/videos/generations \
  -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{"model": "pixverse-lipsync", "prompt": "sunrise over the ocean", "duration": 6}'
```

## Parameters

| Parameter                 | Type   | Required | Default  | Description                                                                                                                                                                                                                                                 |
| ------------------------- | ------ | -------- | -------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `lip_sync_tts_content`    | string | no       | -        | The line to speak. Used when no audio file is attached. Billed in 15-character blocks.                                                                                                                                                                      |
| `lip_sync_tts_speaker_id` | enum   | no       | `"Auto"` | Voice used for the spoken line. Auto picks one to suit the clip. Ignored when an audio file is attached. · Allowed: `Auto`, `Emily`, `James`, `Isabella`, `Liam`, `Chloe`, `Adrian`, `Harper`, `Ava`, `Sophia`, `Julia`, `Mason`, `Jack`, `Oliver`, `Ethan` |
| `video`                   | string | no       | -        | Source video URL. Required.                                                                                                                                                                                                                                 |
| `audio`                   | string | no       | -        | Audio URL to lip sync to. Takes precedence over the spoken text.                                                                                                                                                                                            |

## Notes

Aligns mouth movement in an existing video to speech, either from an audio file you supply or from text spoken by a built-in voice.

**Inputs**

* `video`: the source clip, up to 300 seconds and 250MB.
* `audio`: the speech to match, up to 300 seconds and 250MB.
* Or `lip_sync_tts_content` with `lip_sync_tts_speaker_id` to have the model speak your text. Fourteen named voices are available plus `Auto`, which picks one to suit the clip.

**Billing**

* Billed per second of speech. Text-to-speech input is metered in 15-character blocks at the same rate, so the charge tracks the length of the script rather than the length of the source video.

**Input limits**

* Video: MP4, MOV or WebM, up to 1920px on the long edge.
* Audio: MP3, WAV, M4A or AAC.

---

*Machine-readable schema:* `GET https://api.empiriolabs.ai/v1/models/pixverse-lipsync`.