# Sam Audio · Span Separate API

> Isolates a sound from audio using time spans you provide, with an optional text hint

Instead of relying on text alone, you pass `spans` marking when the target sound occurs in the `audio_url`. A `prompt` is optional but helps identify the sound type. `trim_to_span` can cut the output to the span range, and `use_sound_activity_ranking` allows reranking without a prompt. Returns `target` and `residual` audio in wav or mp3.

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

## Pricing

Price: **from $0.05 / 30 seconds of input audio** (the lowest tier; the quote prices your exact input). Price per 30 seconds of your input audio: 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 audio × $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/span-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 |
|---|---|---|---|---|---|---|
| `audio_url` | `audio` | string (audio URL) | yes |  |  | Audio file URL for processing. |
| `prompt` |  | string \| null | no |  |  | Sound-identification aid for extracting audio from the span. A text description of the sound to isolate is recommended, though not required. |
| `spans` |  | array of object {start, end, include} | yes |  |  | Time intervals containing the target sound to isolate. |
| `spans[].start` |  | number | yes |  | ≥ 0 | Span start timestamp, measured in seconds. |
| `spans[].end` |  | number | yes |  | ≥ 0 | Span end timestamp, measured in seconds. |
| `spans[].include` |  | boolean | no | `true` |  | Inclusion of sounds within the span: True includes them, while False excludes them. |
| `reranking_candidates` |  | integer | no | `1` | 1 – 7 | Candidate count used only with a text prompt: that many candidates are generated and ranked. Span-only separation ignores this setting. |
| `acceleration` |  | enum (string) | no | `balanced` | `fast`, `balanced`, `quality` | Acceleration level applied to processing. |
| `max_chunk_duration` |  | number | no | `60` | 10 – 60 | Per-pass audio limit, measured in seconds, beyond which processing uses overlapping chunks that are blended together. |
| `chunk_overlap` |  | number | no | `5` | 0 – 30 | Length of the overlap between chunks, measured in seconds, used for crossfade blending. |
| `use_sound_activity_ranking` |  | boolean | no | `false` |  | Sound-activity ranking option requiring reranking_candidates > 1, enabling effective reranking for span-only separation without a text prompt. Candidates are scored by how closely their detected nonsilent regions align with the supplied spans. |
| `trim_to_span` |  | boolean | no | `false` |  | Output-length choice between the specified span alone and the complete audio. Enabling it trims to the span's time range; False retains full length and isolates the target sound throughout. |
| `output_format` |  | enum (string) | no | `wav` | `wav`, `mp3` | Format for the generated audio. |

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",
  "spans": [
    {
      "end": 10,
      "include": true,
      "start": 6
    }
  ]
}
```

A fuller example:

```json
{
  "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
  "spans": [
    {
      "end": 10,
      "include": true,
      "start": 6
    }
  ]
}
```

## 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/span-separate?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",
    "spans": [
      {
        "end": 10,
        "include": true,
        "start": 6
      }
    ]
  }'

# 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/span-separate?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
    "spans": [
      {
        "end": 10,
        "include": true,
        "start": 6
      }
    ]
  }),
});
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 = {
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
    "spans": [
        {
            "end": 10,
            "include": True,
            "start": 6,
        },
    ],
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/sam-audio/span-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/span-separate",
      "input": {
        "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
        "spans": [
          {
            "end": 10,
            "include": true,
            "start": 6
          }
        ]
      },
      "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/span-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": {
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
    "spans": [
      {
        "end": 10,
        "include": true,
        "start": 6
      }
    ]
  },
  "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} | Target sound extracted in isolation. |
| `residual` | object {url, content_type, file_name, file_size} | Audio remaining apart from the target sound. |
| `duration` | number | Output audio length, measured in seconds. |
| `sample_rate` | integer | Sampling frequency in Hz for the output audio. |

## 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 · Visual Separate](https://doitong.com/developers/models/sam-audio/visual-separate.md) (`sam-audio/visual-separate`): from $0.05 / 30 seconds of input video
- [MMAudio V2](https://doitong.com/developers/models/mmaudio-v2.md) (`mmaudio-v2`): $0.001 / second
- [Demucs](https://doitong.com/developers/models/demucs.md) (`demucs`): $0.0007 / second of input audio
- [DeepFilterNet 3](https://doitong.com/developers/models/deepfilternet3.md) (`deepfilternet3`): $0.001 / second of input audio
- [ElevenLabs Audio Isolation](https://doitong.com/developers/models/elevenlabs/audio-isolation.md) (`elevenlabs/audio-isolation`): $0.10 / minute of input file
- [Elevenlabs Sound Effects V2](https://doitong.com/developers/models/elevenlabs/sound-effects/v2.md) (`elevenlabs/sound-effects/v2`): $0.002 / second
- [ElevenLabs Voice Changer](https://doitong.com/developers/models/elevenlabs/voice-changer.md) (`elevenlabs/voice-changer`): $0.30 / minute of input audio

## Links

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