# Longcat Single Avatar · Audio to Video API

> Tạo video avatar nói chuyện chỉ bằng tệp âm thanh và lời nhắc văn bản, không cần hình ảnh nguồn

Tạo video avatar đồng bộ môi từ `audio_url` và `prompt` mô tả người. Đầu ra là 480p hoặc 720p. `num_segments` (1 đến 10) đặt độ dài: phân đoạn đầu khoảng 5.8 giây, mỗi phân đoạn tiếp theo thêm 5 giây. `audio_guidance_scale` (1 đến 10) kiểm soát mức độ âm thanh chi phối khẩu hình; giá trị cao hơn có thể làm chuyển động cường điệu.

- Model id: `longcat-single-avatar/audio-to-video`
- Made by: Meituan
- Category: Lipsync & Avatars
- Output: video
- Price per second of your output video: from $0.15 / second of output video (cheapest run $0.15 (150 API credits))
- Run: `POST https://api.doitong.ru/v1/run/longcat-single-avatar/audio-to-video`
- Quote: `POST https://api.doitong.ru/v1/quote/longcat-single-avatar/audio-to-video`
- Docs page: https://doitong.com/vi/developers/models/longcat-single-avatar/audio-to-video

## Pricing

Price: **from $0.15 / second of output video** (the lowest tier; the quote prices your exact input). Price per second of your output video: the input files are measured before the run (length, resolution, frame rate). The quote measures the same files and is exactly what the run charges.

Price by tier:

- base rate: $0.15 / second of output video
- 720p: $0.60 / second of output video

The full example input below costs $0.90 = 900 API credits (6 s output video × $0.15).

Prices are the upstream price in USD, paid from the API balance in API credits (1000 API credits = 1 USD). `POST https://api.doitong.ru/v1/quote/longcat-single-avatar/audio-to-video` with the same JSON body returns the exact price for that input; the quote is exactly what a run charges. Invalid input is never charged and failed or canceled requests are refunded automatically.

## Input parameters

Send either the canonical name or the native field name (not both). Canonical names are the same across models.

| Parameter | Canonical name | Type | Required | Default | Allowed values / range | Description |
|---|---|---|---|---|---|---|
| `audio_url` | `audio` | string (audio URL) | yes |  |  | URL tệp âm thanh dùng để điều khiển avatar. |
| `prompt` |  | string | no | `A person is talking naturally with natural expressions and movements.` |  | Lời nhắc định hướng việc tạo sinh video. |
| `negative_prompt` |  | string | no | `Close-up, Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards` |  | Lời nhắc phủ định xác định nội dung mà quá trình tạo sinh video cần tránh. |
| `num_inference_steps` |  | integer | no | `50` | 10 – 100 | Số bước suy luận đã thực hiện. |
| `text_guidance_scale` |  | number | no | `4` | 1 – 10 | Thang tỷ lệ hướng dẫn văn bản được áp dụng trong classifier-free guidance. |
| `audio_guidance_scale` |  | number | no | `4` | 1 – 10 | Điều chỉnh hướng dẫn âm thanh, có thể phóng đại chuyển động miệng khi tăng giá trị. |
| `resolution` |  | enum (string) | no | `480p` | `480p`, `720p` | Độ phân giải video đầu ra, entweder 480p hoặc 720p. |
| `num_segments` |  | integer | no | `1` | 1 – 10 | Số phân đoạn video, với khoảng 5.8s cho phân đoạn đầu tiên và 5s cho mỗi phân đoạn tiếp theo—xấp xỉ 5 giây video mỗi phân đoạn. |
| `seed` |  | integer \| null | no |  |  | Giá trị seed khởi tạo quá trình tạo số ngẫu nhiên. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Công tắc kiểm tra an toàn phụ thuộc quyền tài khoản: các yêu cầu không được ủy quyền vẫn bắt buộc kiểm tra và cần có ủy quyền để tắt. |
| `enable_prompt_expansion` |  | boolean | no | `false` |  | Công tắc mở rộng lời nhắc dựa trên LLM để cải thiện chất lượng video thông qua lời nhắc nâng cao. |

File parameters (`audio`) take a public `https://` URL, a `data:` URI up to 10 MB, or the `file_url` of an upload from `POST /files`.

## Example input

Required parameters only:

```json
{
  "audio": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
}
```

A fuller example:

```json
{
  "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
}
```

## Run it

Set `DOITONG_API_KEY` to a key from https://doitong.com/developers/dashboard#keys. `?wait=20` returns the finished request in the same call when it is ready within 20 seconds; otherwise poll `GET /requests/{id}` (it also accepts `?wait=`), or pass `webhook_url`.

### curl

```bash
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.ru/v1/run/longcat-single-avatar/audio-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"
```

### JavaScript

```javascript
const API = "https://api.doitong.ru/v1";
const headers = {
  "Authorization": "Bearer " + process.env.DOITONG_API_KEY,
  "Content-Type": "application/json",
};

// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/longcat-single-avatar/audio-to-video?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  }),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);

// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
  res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
  request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
```

### Python

```python
import os
import requests

API = "https://api.doitong.ru/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/longcat-single-avatar/audio-to-video", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
    raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])

# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
    request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
    raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])
```

### MCP

The MCP server at `https://api.doitong.ru/v1/mcp` exposes the tools `search_models`, `get_model`, `quote`, `run`, `get_request`, `cancel_request`, `list_requests`, `create_upload` and `get_account`. A `run` call for this model:

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "run",
    "arguments": {
      "model_id": "longcat-single-avatar/audio-to-video",
      "input": {
        "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
      },
      "wait_seconds": 20
    }
  }
}
```

## Response

Every call returns a request object. `status` is one of `queued`, `running`, `succeeded`, `failed`, `canceled`. `outputs` lists the generated files with URLs on our storage (kept forever, or 7 days with `?storage=temporary`; `storage` says which); `output` is the model's own result object with the same URLs.

```json
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "longcat-single-avatar/audio-to-video",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 900,
    "usd": "0.90",
    "charged": 900,
    "refunded": 0
  },
  "input": {
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  },
  "output": {
    "video": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_name": "0-output.mp4",
      "file_size": 1843200
    },
    "seed": 42
  },
  "outputs": [
    {
      "type": "video",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_size": 1843200,
      "width": 1280,
      "height": 720,
      "duration": 5,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `video` | object {url, content_type, file_name, file_size} | Tệp video được tạo sinh. |
| `seed` | integer | Giá trị seed được áp dụng trong quá trình tạo sinh. |

## Related models

- [Longcat Single Avatar · Image Audio to Video](https://doitong.com/developers/models/longcat-single-avatar/image-audio-to-video.md) (`longcat-single-avatar/image-audio-to-video`): from $0.15 / second of output video
- [Kling AI Avatar 2.0 Pro](https://doitong.com/developers/models/kling-video/ai-avatar/v2/pro.md) (`kling-video/ai-avatar/v2/pro`): $0.115 / second of input audio
- [Sync Lipsync 3](https://doitong.com/developers/models/sync-lipsync/v3.md) (`sync-lipsync/v3`): $8.00 / minute of output video
- [VEED Fabric 1.0](https://doitong.com/developers/models/veed/fabric-1.0.md) (`veed/fabric-1.0`): from $0.08 / second of input audio
- [Infinitalk](https://doitong.com/developers/models/infinitalk.md) (`infinitalk`): from $0.20 / second of output video
- [Infinitalk · Single Text](https://doitong.com/developers/models/infinitalk/single-text.md) (`infinitalk/single-text`): from $2.32 / run
- [Infinitalk · Video to Video](https://doitong.com/developers/models/infinitalk/video-to-video.md) (`infinitalk/video-to-video`): from $0.30 / second of output video
- [AI Avatar Multi](https://doitong.com/developers/models/ai-avatar/multi.md) (`ai-avatar/multi`): from $0.20 / second of output video

## Links

- HTML page: https://doitong.com/developers/models/longcat-single-avatar/audio-to-video
- All models and guides for AI agents: https://doitong.com/developers/llms.txt
- OpenAPI 3.1 with this model's typed request body: https://doitong.com/developers/openapi.json?model=longcat-single-avatar/audio-to-video
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.ru/v1/models/longcat-single-avatar/audio-to-video