# Sam Audio · Visual Separate API

> 從影片音軌中分離聲音，可選擇以遮罩影片與文字提示引導

接收 `video_url` 並從其音訊中擷取目標聲音。可選的 `mask_video_url` 標示目標物件（黑色代表目標，白色代表背景），`prompt` 可加入文字提示。最多可排序 4 個 `reranking_candidates`，長音訊會分塊處理。輸出包含 wav 或 mp3 格式的 `target` 和 `residual` 音訊。

- Model id: `sam-audio/visual-separate`
- Made by: Meta
- Category: Video to Audio
- Output: json
- Price per 30 seconds of your input video: from $0.05 / 30 seconds of input video (cheapest run $0.05 (50 API credits))
- Run: `POST https://api.doitong.com/v1/run/sam-audio/visual-separate`
- Quote: `POST https://api.doitong.com/v1/quote/sam-audio/visual-separate`
- Docs page: https://doitong.com/zh-TW/developers/models/sam-audio/visual-separate

## Pricing

Price: **from $0.05 / 30 seconds of input video** (the lowest tier; the quote prices your exact input). Price per 30 seconds of your input 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.

The full example input below costs $0.05 = 50 API credits (1 × 30 s input video × $0.05).

Prices are the upstream price in USD, paid from the API balance in API credits (1000 API credits = 1 USD). `POST https://api.doitong.com/v1/quote/sam-audio/visual-separate` 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 |
|---|---|---|---|---|---|---|
| `video_url` | `video` | string (video URL) | yes |  |  | 用於處理的影片檔案 URL，格式例如 MP4 或 MOV。 |
| `mask_video_url` |  | string (video URL) \| null | no |  |  | 使用二進位編碼的遮罩影片 URL，其中目標物件為黑色，背景為白色。 |
| `prompt` |  | string | no | `` |  | 用於協助分離的目標聲音自然語言描述。 |
| `reranking_candidates` |  | integer | no | `1` | 1 – 4 | 為排名生成的候選項目數量。 |
| `acceleration` |  | enum (string) | no | `balanced` | `fast`, `balanced`, `quality` | 套用至處理的加速等級。 |
| `max_chunk_duration` |  | number | no | `60` | 10 – 60 | 每次處理的音訊長度上限，以秒計；超過此長度時，處理會使用重疊區塊並將其混合。 |
| `chunk_overlap` |  | number | no | `5` | 0 – 30 | 區塊重疊長度，以秒計，用於交叉淡化混合。 |
| `output_format` |  | enum (string) | no | `wav` | `wav`, `mp3` | 生成音訊的格式。 |

File parameters (`video`, `mask_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
{
  "video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
}
```

A fuller example:

```json
{
  "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/sam-audio/visual-separate?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "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/sam-audio/visual-separate?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "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 = {
    "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/sam-audio/visual-separate", 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": "sam-audio/visual-separate",
      "input": {
        "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": "sam-audio/visual-separate",
  "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": 50,
    "usd": "0.05",
    "charged": 50,
    "refunded": 0
  },
  "input": {
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  },
  "output": {
    "target": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    },
    "residual": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    },
    "duration": 5,
    "sample_rate": 48000
  },
  "outputs": [
    {
      "type": "file",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_size": 1843200,
      "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 |
|---|---|---|
| `target` | object {url, content_type, file_name, file_size} | 單獨擷取的目標聲音。 |
| `residual` | object {url, content_type, file_name, file_size} | 除目標聲音以外的剩餘音訊。 |
| `duration` | number | 輸出音訊長度，以秒計。 |
| `sample_rate` | integer | 輸出音訊的取樣頻率（Hz）。 |

## Related models

- [Sam Audio · Separate](https://doitong.com/developers/models/sam-audio/separate.md) (`sam-audio/separate`): from $0.05 / 30 seconds of input audio
- [Sam Audio · Span Separate](https://doitong.com/developers/models/sam-audio/span-separate.md) (`sam-audio/span-separate`): from $0.05 / 30 seconds of input audio
- [Hunyuan Video Foley](https://doitong.com/developers/models/hunyuan-video-foley.md) (`hunyuan-video-foley`): $0.10 / 10 seconds of input video
- [Kling Video · Video to Audio](https://doitong.com/developers/models/kling-video/video-to-audio.md) (`kling-video/video-to-audio`): $0.035 / video
- [Mirelo SFX2.0 · Video to Audio](https://doitong.com/developers/models/mirelo-ai/sfx2.0/video-to-audio.md) (`mirelo-ai/sfx2.0/video-to-audio`): $0.01 / second of output audio
- [PixVerse Sound Effects](https://doitong.com/developers/models/pixverse/sound-effects.md) (`pixverse/sound-effects`): $0.10 / 5 seconds of input video
- [Sonilo V1.1](https://doitong.com/developers/models/sonilo/v1.1/video-to-music.md) (`sonilo/v1.1/video-to-music`): $0.009 / second of output audio
- [Sonilo V1.1 Video to Sound Effects](https://doitong.com/developers/models/sonilo/v1.1/video-to-sound-effects.md) (`sonilo/v1.1/video-to-sound-effects`): $0.009 / second of input video

## Links

- HTML page: https://doitong.com/developers/models/sam-audio/visual-separate
- 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=sam-audio/visual-separate
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/sam-audio/visual-separate