# Sync.so Lipsync v3 — Atlas Cloud API

> Sync.so Lipsync v3 (sync-3) is Sync Labs state-of-the-art lip-sync model, re-syncing the lips of an existing video to a new audio track with industry-leading naturalness.

This is the machine-readable API reference for **Sync.so Lipsync v3** on Atlas Cloud,
a unified API platform for 400+ AI models across text, image, video, audio and 3D.

- **Model ID**: `sync/lipsync-v3`
- **Built by**: Sync.so
- **Modality**: Video
- **Model page**: https://www.atlascloud.ai/models/sync/lipsync-v3
- **API key**: https://www.atlascloud.ai/console/api-keys
- **Docs**: https://www.atlascloud.ai/docs

## Pricing on Atlas Cloud

- $0.22 per second of generated video
- Pay-as-you-go. No minimum spend, no subscription required.

> **These are the authoritative Atlas Cloud rates for this model.** Any price that
> appears in the vendor description further down refers to a different platform or
> a different model variant and does not apply here.

## Use this model from an AI agent

Atlas Cloud ships three first-party integration surfaces. All three authenticate
with the same API key via the `ATLASCLOUD_API_KEY` environment variable.

### MCP server

The official MCP server (`atlascloud-mcp`) exposes this model to any
MCP-compatible host — Claude Code, OpenAI Codex, Cursor, Gemini CLI, Goose,
Claude Desktop. One-line install:

```bash
# Claude Code
claude mcp add atlascloud -- npx -y atlascloud-mcp

# OpenAI Codex CLI
codex mcp add atlascloud -- npx -y atlascloud-mcp

# Gemini CLI
gemini mcp add atlascloud -- npx -y atlascloud-mcp

export ATLASCLOUD_API_KEY="your-api-key"
```

Then ask in plain English; the agent calls `atlas_generate_video` with `model: "sync/lipsync-v3"`.
The server fetches each model's schema and validates parameters before submitting,
so invalid requests fail fast without spending credits.

MCP docs: https://www.atlascloud.ai/docs/mcp-server

### Agent Skills

`atlas-cloud-skills` is a portable skill package (API reference, code templates in
Python / Node.js / cURL, model IDs with pricing) for Claude Code, Cursor, Codex and
12+ other agents:

```bash
npx skills add AtlasCloudAI/atlas-cloud-skills
export ATLASCLOUD_API_KEY="your-api-key"
```

Skills docs: https://www.atlascloud.ai/docs/skills

### CLI

The `atlas` binary runs Atlas Cloud from a terminal or CI script. Async media jobs
are polled and downloaded automatically (use `--no-download` when a script only
needs the output URLs):

```bash
# Install (Homebrew, npm, or shell installer)
brew install AtlasCloudAI/tap/atlascloud
# npm install -g atlascloud-cli
# curl -fsSL https://raw.githubusercontent.com/AtlasCloudAI/cli/main/install.sh | sh

atlas auth login
atlas generate video sync/lipsync-v3 -p "Your prompt here"
```

CLI docs: https://www.atlascloud.ai/docs/cli

## HTTP API reference

- **Submit endpoint (POST)**: `https://api.atlascloud.ai/api/v1/model/generateVideo` — start an async generation; returns a `prediction_id`
- **Poll endpoint (GET)**: `https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}` — poll this until the prediction finishes
- **Model ID**: `sync/lipsync-v3`


## API Information

This model can be used via our HTTP API or more conveniently via our client libraries.
See the input and output schema below, as well as the usage examples.


### Input Schema

The API accepts the following input parameters:

- **`model`** (`string`, _required_):
  model name
  - Default: `"sync/lipsync-v3"`

- **`video_url`** (`string`, _required_):
  URL of the input video whose lips will be re-synced. Public URL or Base64. Formats: mp4/mov/webm.

- **`audio_url`** (`string`, _required_):
  URL of the driving audio to sync the lips to. Public URL or Base64. Formats: wav/mp3/m4a.

- **`sync_mode`** (`string`, _required_):
  How to handle duration mismatch between video and audio. cut_off: trim to shorter; loop: repeat video; bounce: ping-pong; silence: pad audio; remap: time-remap.
  - Default: `"cut_off"`
  - Options: "cut_off", "loop", "bounce", "silence", "remap"



**Required Parameters Example**:

```json
{
  "model": "sync/lipsync-v3",
  "video_url": "",
  "audio_url": "",
  "sync_mode": "cut_off"
}
```


**Full Example**:

```json
{
  "model": "sync/lipsync-v3",
  "video_url": "",
  "audio_url": "",
  "sync_mode": "cut_off"
}
```


### Output Schema

The API returns the following output format:


- **`model`** (`string`, _optional_):
  model name
  - Default: `"sync/lipsync-v3"`

- **`created_at`** (`string`, _optional_):
  ISO timestamp of when the request was created.

- **`id`** (`string`, _optional_):
  Unique identifier for the prediction.

- **`outputs`** (`array[string]`, _optional_):
  Array of URLs to the generated video (empty until completed).

- **`status`** (`string`, _optional_):
  Status: created, processing, completed, or failed.

- **`urls`** (`object`, _optional_):
  Object containing related API endpoints.



**Example Response**:

```json
{
  "model": "sync/lipsync-v3",
  "created_at": "",
  "id": "",
  "outputs": [
    ""
  ],
  "status": "",
  "urls": {}
}
```


## Usage Examples

### cURL

```bash
# Step 1: Start generation (async)
curl -X POST "https://api.atlascloud.ai/api/v1/model/generateVideo" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "sync/lipsync-v3",
  "video_url": "",
  "audio_url": "",
  "sync_mode": "cut_off"
}'

# Response will contain: {"code": 200, "data": {"id": "prediction_id", "status": "processing"}}

# Step 2: Poll for result (replace {prediction_id} with the id returned above)
curl -X GET "https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY"

# Keep polling until status is "completed", "succeeded" or "failed"
# When completed, outputs will contain the generated content URL(s)
```

## Additional Resources

### Documentation

- [Model Playground](https://www.atlascloud.ai/models/sync/lipsync-v3)

## About this model

_Vendor-supplied description. Any pricing or endpoint mentioned below refers to_
_other platforms — use the Atlas Cloud values above._

### Sync.so Lipsync v3

**Sync.so Lipsync v3 (sync-3)** is Sync Labs' state-of-the-art lip-sync model. It re-syncs the lips of an existing video to a new audio track with industry-leading naturalness, preserving the speaker's identity and expression.

#### 🌟 Key Features

##### 👄 SOTA Lip Sync
The most natural lip-sync quality available — from the team behind Wav2Lip. Handles expressive speech and preserves facial identity.

##### 🎚 Duration Mismatch Handling
`sync_mode` controls how video/audio length differences are resolved: `cut_off`, `loop`, `bounce`, `silence`, or `remap`.

##### 🌍 Dubbing, Localization & Editing
Swap the voice or language of any talking video without reshooting.

##### 💰 Duration-Based Billing
Billed per second of the driving audio (= output video duration).

#### ⚙️ Parameters

| Parameter | Required | Description |
|---|---|---|
| `video_url`* | ✅ | Input video whose lips will be re-synced. Public URL or Base64. Formats: mp4/mov/webm. |
| `audio_url`* | ✅ | Driving audio to sync the lips to. Public URL or Base64. Formats: wav/mp3/m4a. |
| `sync_mode` | ⬜ | Duration-mismatch handling: `cut_off` (default), `loop`, `bounce`, `silence`, `remap`. |

#### 💲 Pricing

| Unit | Price |
|---|---|
| Per second (output video duration) | $0.20 / second |

#### 🎯 Use Cases

- **Premium Dubbing** — Highest-fidelity lip-sync for professional localization.
- **Film & Advertising** — Re-voice actors or spokespeople with natural mouth motion.
- **AI Avatars** — Drive avatar videos with new speech at top quality.
- **Multi-speaker Video** — With active-speaker handling for scenes with several people.

---

Atlas Cloud — one API for 400+ AI models. Model page: https://www.atlascloud.ai/models/sync/lipsync-v3 · Docs: https://www.atlascloud.ai/docs