# Sad Talker · Reference API

> Tạo hoạt ảnh khuôn mặt nói chuyện từ ảnh và âm thanh, với tư thế đầu lấy từ video tham chiếu

Giống biến thể khuôn mặt nói cơ bản, nhưng cũng yêu cầu `reference_pose_video_url`, một video có chuyển động đầu hướng dẫn kết quả. Đầu vào là `source_image_url` và `driven_audio_url`. Các tùy chọn gồm `pose_style` (0 đến 45), `expression_scale` (0 đến 3), `face_model_resolution` (256 hoặc 512), `still_mode` và lựa chọn trong năm chế độ `preprocess`.

- Model id: `sadtalker/reference`
- Made by: Open model
- Category: Lipsync & Avatars
- Output: video
- Charged by usage (up to $4.50 per run, typical $0.042; the rest of the hold is refunded): $0.00125 / second of processing time (cheapest run $0.042 (42 API credits))
- Run: `POST https://api.doitong.com/v1/run/sadtalker/reference`
- Quote: `POST https://api.doitong.com/v1/quote/sadtalker/reference`
- Docs page: https://doitong.com/vi/developers/models/sadtalker/reference

## Pricing

Price: **$0.00125 / second of processing time**. Charged by actual usage at $0.00125 / second of processing time: up to $4.50 per run (the quote gives the maximum for your input), the rest is refunded automatically after the run. A typical run costs $0.042.

The full example input below holds up to $4.50 = 4500 API credits (up to 3600 s of processing time × $0.00125) when it starts; a typical run costs $0.042 (42 API credits).

Prices are the upstream price in USD, paid from the API balance in API credits (1000 API credits = 1 USD). This model is charged by usage: `POST https://api.doitong.com/v1/quote/sadtalker/reference` with the same JSON body returns the most the run can cost for that input (`credits`, debited when the run starts); after the run you pay the usage the model reports and the rest is refunded automatically. An input whose maximum would exceed the per-run limit is refused with 422. 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 |
|---|---|---|---|---|---|---|
| `source_image_url` | `image` | string (image URL) | yes |  |  | Vị trí hình ảnh nguồn dưới dạng URL. |
| `driven_audio_url` |  | string (audio URL) | yes |  |  | URL trỏ đến âm thanh điều khiển. |
| `reference_pose_video_url` |  | string (video URL) | yes |  |  | URL của video tham chiếu. |
| `pose_style` |  | integer | no | `0` | 0 – 45 | Phong cách dùng cho tư thế. |
| `face_model_resolution` |  | enum (string) | no | `256` | `256`, `512` | Độ phân giải mô hình khuôn mặt sử dụng. |
| `expression_scale` |  | number | no | `1` | 0 – 3 | Hệ số tỷ lệ cho biểu cảm. |
| `face_enhancer` |  | string \| null | no |  |  | Loại bộ tăng cường khuôn mặt cần áp dụng. |
| `still_mode` |  | boolean | no | `false` |  | Chế độ ảnh tĩnh để giảm chuyển động đầu khi sử dụng tiền xử lý `full`. |
| `preprocess` |  | enum (string) | no | `crop` | `crop`, `extcrop`, `resize`, `full`, `extfull` | Phương pháp tiền xử lý cần áp dụng. |

File parameters (`image`, `driven_audio_url`, `reference_pose_video_url`) 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
{
  "image": "https://content.doitong.com/images/showcase/v3/avatar/talking_avatar.jpg",
  "driven_audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
  "reference_pose_video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
}
```

A fuller example:

```json
{
  "source_image_url": "https://content.doitong.com/images/showcase/v3/avatar/talking_avatar.jpg",
  "driven_audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
  "reference_pose_video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
}
```

## 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.com/v1/run/sadtalker/reference?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "source_image_url": "https://content.doitong.com/images/showcase/v3/avatar/talking_avatar.jpg",
    "driven_audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
    "reference_pose_video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  }'

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

### JavaScript

```javascript
const API = "https://api.doitong.com/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/sadtalker/reference?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "source_image_url": "https://content.doitong.com/images/showcase/v3/avatar/talking_avatar.jpg",
    "driven_audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
    "reference_pose_video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  }),
});
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.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "source_image_url": "https://content.doitong.com/images/showcase/v3/avatar/talking_avatar.jpg",
    "driven_audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
    "reference_pose_video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/sadtalker/reference", 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.com/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": "sadtalker/reference",
      "input": {
        "source_image_url": "https://content.doitong.com/images/showcase/v3/avatar/talking_avatar.jpg",
        "driven_audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
        "reference_pose_video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
      },
      "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": "sadtalker/reference",
  "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": 4500,
    "usd": "4.50",
    "charged": 4500,
    "refunded": 0
  },
  "input": {
    "source_image_url": "https://content.doitong.com/images/showcase/v3/avatar/talking_avatar.jpg",
    "driven_audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
    "reference_pose_video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  },
  "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
    }
  },
  "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.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `video` | object {url, content_type, file_name, file_size} | URL của video được tạo. |

## Related models

- [Sad Talker](https://doitong.com/developers/models/sadtalker.md) (`sadtalker`): $0.00125 / second of processing time
- [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
- [AI Avatar Multi](https://doitong.com/developers/models/ai-avatar/multi.md) (`ai-avatar/multi`): from $0.20 / second of output video
- [AI Avatar Multi Text](https://doitong.com/developers/models/ai-avatar/multi-text.md) (`ai-avatar/multi-text`): from $0.648 / run
- [AI Avatar Single Text](https://doitong.com/developers/models/ai-avatar/single-text.md) (`ai-avatar/single-text`): from $4.688 / run
- [Flashhead](https://doitong.com/developers/models/flashhead.md) (`flashhead`): $0.068 / run

## Links

- HTML page: https://doitong.com/developers/models/sadtalker/reference
- 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=sadtalker/reference
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/sadtalker/reference