# VEED Clean Audio API

> 잡음이 있는 녹음이나 영상의 오디오 트랙을 정리하고 음량을 정규화하는 음성 잡음 제거기

음성 녹음에서 배경 잡음을 제거합니다. `audio_url`은 ffmpeg가 디코딩할 수 있는 모든 오디오 또는 비디오 형식을 받습니다. `strength`(0-1)는 음성 구간에 적용할 억제 강도를 설정하고, `target_lufs`(-40~-8)는 출력 음량을 설정하며 생략할 수도 있습니다. 출력은 입력과 같은 길이의 48 kHz 모노 16비트 flac 또는 wav입니다.

- Model id: `veed/clean-audio`
- Made by: VEED
- Category: Audio
- Output: audio
- Price per minute of your input audio: $0.0125 / minute of input audio (cheapest run $0.013 (13 API credits))
- Run: `POST https://api.doitong.com/v1/run/veed/clean-audio`
- Quote: `POST https://api.doitong.com/v1/quote/veed/clean-audio`
- Docs page: https://doitong.com/ko/developers/models/veed/clean-audio

## Pricing

Price: **$0.0125 / minute of input audio**. Price per minute 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 $0.013 = 13 API credits (1 min input audio × $0.0125).

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/veed/clean-audio` 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 |  |  | 공개 URL 또는 data URI로 제공하는 정리 대상 녹음입니다. wav, ogg, mp3, webm, m4a, mov, aac 및 mp4를 포함해 ffmpeg로 디코딩할 수 있는 모든 오디오 또는 동영상을 허용합니다. 동영상에서는 오디오 트랙을 처리합니다. 정리된 오디오가 포함된 동영상을 받으려면 /video를 호출하며, 다중 채널 녹음은 모노로 다운믹스됩니다. 최대 길이는 30분이고 크기 제한은 512 MB입니다. |
| `strength` |  | number | no | `0.874` | 0 – 1 | 음성 배경 억제 강도입니다. 낮은 설정은 음성 아래의 실내 잔향을 더 많이 유지하지만 단어 사이의 일시 정지는 설정과 관계없이 완전히 정리됩니다. 남는 원본 소리의 하한은 1에서 strength를 뺀 값이며, 기본값 0.874는 검증된 -18 dB 설정에 해당합니다. |
| `target_lufs` |  | number \| null | no | `-19` | -40 – -8 | ITU-R BS.1770 기준 통합 출력 라우드니스 목표입니다. API를 통해 null을 제공하면 정규화를 건너뛰고 소스 레벨을 유지합니다. 그렇지 않으면 기본값은 VEED 편집기가 제공하는 값과 같은 -19 LUFS이며, true-peak 상한은 -1.1 dBTP입니다. |
| `output_format` |  | enum (string) | no | `flac` | `flac`, `wav` | 오디오 컨테이너 선택입니다. FLAC은 WAV의 약 절반 크기로 무손실 품질을 유지합니다. 출력은 48 kHz, 16비트 샘플의 단일 채널입니다. |

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.com/v1/run/veed/clean-audio?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.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/veed/clean-audio?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.com/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/veed/clean-audio", 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": "veed/clean-audio",
      "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": "veed/clean-audio",
  "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": 13,
    "usd": "0.013",
    "charged": 13,
    "refunded": 0
  },
  "input": {
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  },
  "output": {
    "audio": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp3",
      "content_type": "audio/mpeg",
      "file_name": "0-output.mp3",
      "file_size": 1843200
    },
    "audio_duration": 1.0
  },
  "outputs": [
    {
      "type": "audio",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp3",
      "content_type": "audio/mpeg",
      "file_size": 1843200,
      "duration": 12,
      "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 |
|---|---|---|
| `audio` | object {url, content_type, file_name, file_size} | 소스와 동일한 길이의 정리된 오디오이며 라우드니스 정규화가 적용됩니다. 녹음은 단일 채널, 48 kHz 샘플 레이트 및 16비트 깊이를 사용합니다. |
| `audio_duration` | number | 입력 길이이며 초 단위로 측정됩니다. |

## Related models

- [Subtitles](https://doitong.com/developers/models/veed/subtitles.md) (`veed/subtitles`): from $0.10 / minute of input video
- [Fabric 1.0](https://doitong.com/developers/models/veed/fabric-1.0/text.md) (`veed/fabric-1.0/text`): from $2.40 / run
- [Fabric 1.0 Fast](https://doitong.com/developers/models/veed/fabric-1.0/fast.md) (`veed/fabric-1.0/fast`): from $0.10 / second of input audio
- [Lipsync](https://doitong.com/developers/models/veed/lipsync.md) (`veed/lipsync`): $0.40 / 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
- [MMAudio V2](https://doitong.com/developers/models/mmaudio-v2.md) (`mmaudio-v2`): $0.001 / second
- [DeepFilterNet 3](https://doitong.com/developers/models/deepfilternet3.md) (`deepfilternet3`): $0.001 / second of input audio
- [Demucs](https://doitong.com/developers/models/demucs.md) (`demucs`): $0.0007 / second of input audio

## Links

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