# PixVerse | Lip Sync

Pixverse LipSync generates realistic mouth movements that perfectly match the provided audio. It ensures natural expressions and smooth synchronization for any video character.

## API Information

- **Model Slug:** pixverse-lip-sync
- **Branded URL:** https://www.eachlabs.ai/pixverse/pixverse-v4-5/pixverse-lip-sync
- **Provider:** PixVerse
- **Category:** Video to Video
- **Output Type:** video
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** Lip sync pricing is based on video duration. Approximately 4 credits per second of audio. Longer videos cost proportionally more. Example: a 5-second lip sync costs ~20 credits ($0.13), a 10-second clip costs ~40 credits ($0.25).
- **Estimated Processing Time:** 50 seconds
- **Last Updated:** 2026-06-01
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/pixverse-lip-sync

## Pricing

- **Charge Type:** dynamic
- **Pricing Details:** Lip sync pricing is based on video duration. Approximately 4 credits per second of audio. Longer videos cost proportionally more. Example: a 5-second lip sync costs ~20 credits ($0.13), a 10-second clip costs ~40 credits ($0.25).

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| Rule 1 | Lip sync pricing is based on video duration. Approximately 4 credits per second of audio. Longer videos cost proportionally more. Example: a 5-second lip sync costs ~20 credits ($0.13), a 10-second clip costs ~40 credits ($0.25). |

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| video_url | string | Yes | - | - | Video Url . Max 30 second |
| audio_url | string | No | - | - | Audio Url . Max 30 second |
| speaker | string | No | - | {"auto":{"title":"auto","audio":""},"1":{"title":"Emily","audio":"https://storage.googleapis.com/magicpoint/pixverse-sound-effects/preview-Emily.wav"},"2":{"title":"James","audio":"https://storage.googleapis.com/magicpoint/pixverse-sound-effects/preview-James.wav"},"3":{"title":"Isabella","audio":"https://storage.googleapis.com/magicpoint/pixverse-sound-effects/preview-Isabella.wav"},"4":{"title":"Liam","audio":"https://storage.googleapis.com/magicpoint/pixverse-sound-effects/preview-Liam.wav"},"5":{"title":"Chloe","audio":"https://storage.googleapis.com/magicpoint/pixverse-sound-effects/preview-Chloe.wav"},"6":{"title":"Adrian","audio":"https://storage.googleapis.com/magicpoint/pixverse-sound-effects/preview-Adrian.wav"},"7":{"title":"Harper","audio":"https://storage.googleapis.com/magicpoint/pixverse-sound-effects/preview-Harper.wav"},"8":{"title":"Ava","audio":"https://storage.googleapis.com/magicpoint/pixverse-sound-effects/preview-Ava.wav"},"9":{"title":"Sophia","audio":"https://storage.googleapis.com/magicpoint/pixverse-sound-effects/preview-Sophia.wav"},"10":{"title":"Julia","audio":"https://storage.googleapis.com/magicpoint/pixverse-sound-effects/preview-Julia.wav"},"11":{"title":"Mason","audio":"https://storage.googleapis.com/magicpoint/pixverse-sound-effects/preview-Mason.wav"},"12":{"title":"Jack","audio":"https://storage.googleapis.com/magicpoint/pixverse-sound-effects/preview-Jack.wav"},"13":{"title":"Oliver","audio":"https://storage.googleapis.com/magicpoint/pixverse-sound-effects/preview-Oliver.wav"},"14":{"title":"Ethan","audio":"https://storage.googleapis.com/magicpoint/pixverse-sound-effects/preview-Ethan.wav"}} | - |
| speaker_content | string | No | - | - | - |

## Example Request

```bash
curl -X POST https://api.eachlabs.ai/v1/prediction/ \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "pixverse-lip-sync",
  "input": {
    "video_url": "https://storage.googleapis.com/magicpoint/inputs/pixverse-lipsync-input-video.mp4"
  }
}'
```

## Output Schema

Response returned by `GET /v1/prediction/{id}` when the job completes:

```json
{
  "status": "success",
  "predictionID": "string",
  "output": "string (URL of generated video)",
  "metrics": {
    "predict_time": "number (seconds)"
  }
}
```

## Polling

```bash
curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \
  -H "Authorization: Bearer YOUR_API_KEY"
```

| Status | Meaning |
|--------|---------|
| `processing` | Still running — poll again |
| `success` | Done — read `output` |
| `error` | Failed — read `message` / `details` |

## Webhook (alternative to polling)

Pass `"webhook_url": "https://your.host/path"` in the create request. Eachlabs POSTs this payload when the job ends:

```json
{
  "exec_id": "prediction-uuid",
  "status": "succeeded",
  "output": "https://...",
  "error": ""
}
```

`status` is `"succeeded"` or `"failed"`. `exec_id` equals the `predictionID` from create. Return 2xx within 30 seconds.

## Errors

Error body: `{ "status": "error", "message": "...", "details": "..." }`

| Code | Meaning |
|------|---------|
| `400` | Invalid input |
| `401` | Missing / invalid `Authorization` bearer token |
| `404` | Unknown model or prediction id |
| `429` | Rate limit — 100 creates / min, 10 concurrent per key |
| `5xx` | Retry with backoff |

## Overview

Pixverse LipSync is an advanced AI video generation model designed to create highly realistic mouth movements that are perfectly synchronized with provided audio tracks. Developed by the Pixverse team, the model leverages state-of-the-art deep learning techniques to animate facial regions—especially the lips—so that video characters appear to speak naturally in alignment with any input speech. The model is aimed at both professional and creative users who require seamless audio-to-video synchronization for digital avatars, dubbing, content localization, and character animation.

Key features of Pixverse LipSync include precise phoneme-to-lip mapping, natural facial expressions, and smooth frame transitions, resulting in outputs that closely mimic real human speech patterns. The model stands out for its ability to handle a wide variety of voices, accents, and languages, making it suitable for global content creation. Its underlying technology combines generative adversarial networks (GANs) and temporal convolutional networks, ensuring both high visual fidelity and temporal consistency across video frames. What makes Pixverse LipSync unique is its focus on expressive realism, not just mechanical lip movement, allowing for nuanced emotional delivery and character personality in generated videos.

## Usage Notes

- API Base URL: `https://api.eachlabs.ai/v1`
- Authentication: send `Authorization: Bearer YOUR_API_KEY`. Generate a key from the Eachlabs dashboard at https://www.eachlabs.ai/dashboard/api-keys.
- File-typed parameters (`*_url`, `image_url`, `video_url`, `audio_url`, etc.) accept publicly-reachable HTTPS URLs only. Upload your asset first (GCS / S3 / your CDN) and pass the resulting URL. Data-URIs and localhost URLs are rejected.
- For structured parameters (arrays / objects) send real JSON values, not stringified payloads.
- Monetary values are reported in USD; per-token / per-megapixel rates may be billed in micro-cents internally.
- Prefer `webhook_url` over polling for long-running predictions — see the Webhook Callback section.