# Ffmpeg Api · Loudnorm API

> Chuẩn hóa độ lớn âm thanh theo mục tiêu EBU R128 với các thiết lập LUFS, đỉnh thực và dải động có thể điều chỉnh

Áp dụng chuẩn hóa độ lớn cho tệp tại `audio_url`. Các mục tiêu gồm `integrated_loudness` (-70 đến -5 LUFS), `true_peak` (-9 đến 0 dBTP) và `loudness_range` (1 đến 20 LU). Chế độ động hai lượt là mặc định. Chế độ tuyến tính một lượt cần các giá trị đã đo của đầu vào và có thể trả về bản tóm tắt đo lường.

- Model id: `ffmpeg-api/loudnorm`
- Made by: Utility
- Category: Audio
- Output: audio
- Charged by usage (up to $0.306 per run, typical $0.001; the rest of the hold is refunded): $0.00017 / second of processing time (cheapest run $0.001 (1 API credit))
- Run: `POST https://api.doitong.com/v1/run/ffmpeg-api/loudnorm`
- Quote: `POST https://api.doitong.com/v1/quote/ffmpeg-api/loudnorm`
- Docs page: https://doitong.com/vi/developers/models/ffmpeg-api/loudnorm

## Pricing

Price: **$0.00017 / second of processing time**. Charged by actual usage at $0.00017 / second of processing time: up to $0.306 per run (the quote gives the maximum for your input), the rest is refunded automatically after the run. A typical run costs $0.001.

The full example input below holds up to $0.306 = 306 API credits (up to 1800 s of processing time × $0.00017) when it starts; a typical run costs $0.001 (1 API credit).

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/ffmpeg-api/loudnorm` 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 |
|---|---|---|---|---|---|---|
| `audio_url` | `audio` | string (audio URL) | yes |  |  | URL trỏ đến tệp âm thanh cần chuẩn hóa. |
| `integrated_loudness` |  | number | no | `-18` | -70 – -5 | Giá trị mục tiêu cho độ lớn âm thanh tích hợp, tính bằng LUFS. |
| `true_peak` |  | number | no | `-0.1` | -9 – 0 | Mức trần true-peak, tính bằng dBTP. |
| `loudness_range` |  | number | no | `7` | 1 – 20 | Phạm vi độ lớn âm thanh mục tiêu, tính bằng LU. |
| `offset` |  | number | no | `0` | -99 – 99 | Độ lệch gain, tính bằng dB, được áp dụng trước bộ giới hạn true-peak. |
| `linear` |  | boolean | no | `false` |  | Bộ chọn chế độ chuẩn hóa: false chọn phương pháp động hai lượt có chất lượng cao hơn; true chọn xử lý tuyến tính một lượt. |
| `dual_mono` |  | boolean | no | `false` |  | Xác định đầu vào mono có được xử lý như dual-mono để các phép đo độ lớn EBU R128 chính xác trên hệ thống stereo hay không. |
| `print_summary` |  | boolean | no | `false` |  | Bao gồm bản tóm tắt các phép đo độ lớn cùng với âm thanh đã chuẩn hóa. |
| `measured_i` |  | number \| null | no |  | -99 – 0 | Phép đo độ lớn tích hợp mà chế độ tuyến tính yêu cầu từ tệp đầu vào, được cung cấp theo LUFS. |
| `measured_lra` |  | number \| null | no |  | 0 – 99 | Phép đo phạm vi độ lớn cần cho chế độ tuyến tính, lấy từ tệp đầu vào và cung cấp theo LU. |
| `measured_tp` |  | number \| null | no |  | -99 – 99 | Phép đo true-peak cần cho chế độ tuyến tính, được cung cấp theo dBTP từ tệp đầu vào. |
| `measured_thresh` |  | number \| null | no |  | -99 – 0 | Ngưỡng được đo của âm thanh đầu vào, tính bằng LUFS; bắt buộc khi dùng chế độ tuyến tính. |

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/ffmpeg-api/loudnorm?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/ffmpeg-api/loudnorm?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/ffmpeg-api/loudnorm", 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": "ffmpeg-api/loudnorm",
      "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": "ffmpeg-api/loudnorm",
  "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": 306,
    "usd": "0.306",
    "charged": 306,
    "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
    },
    "summary": {
      "input_integrated": 1.0,
      "input_true_peak": 1.0,
      "input_lra": 1.0,
      "input_threshold": 1.0,
      "output_integrated": 1.0,
      "output_true_peak": 1.0,
      "output_lra": 1.0,
      "output_threshold": 1.0,
      "normalization_type": "string",
      "target_offset": 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} | Tệp âm thanh sau khi chuẩn hóa. |
| `summary` | object {input_integrated, input_true_peak, input_lra, input_threshold, output_integrated, output_true_peak, output_lra, output_threshold, normalization_type, target_offset} \| null | Bản tóm tắt có cấu trúc về các phép đo độ lớn, được trả về khi được yêu cầu. |

## Related models

- [Ffmpeg Api Images to Video](https://doitong.com/developers/models/ffmpeg-api/images-to-video.md) (`ffmpeg-api/images-to-video`): $0.005 / run
- [Ffmpeg Api · Merge Videos](https://doitong.com/developers/models/ffmpeg-api/merge-videos.md) (`ffmpeg-api/merge-videos`): $0.00017 / second of processing time
- [FFmpeg API Metadata](https://doitong.com/developers/models/ffmpeg-api/metadata.md) (`ffmpeg-api/metadata`): $0.001 / run
- [FFmpeg API Waveform](https://doitong.com/developers/models/ffmpeg-api/waveform.md) (`ffmpeg-api/waveform`): $0.001 / run
- [MMAudio V2](https://doitong.com/developers/models/mmaudio-v2.md) (`mmaudio-v2`): $0.001 / second
- [FFmpeg API \[Merge Audios\]](https://doitong.com/developers/models/ffmpeg-api/merge-audios.md) (`ffmpeg-api/merge-audios`): $0.00017 / second of processing time
- [Workflow Utilities Audio Compressor](https://doitong.com/developers/models/workflow-utilities/audio-compressor.md) (`workflow-utilities/audio-compressor`): $0.001 / second of processing time
- [Workflow Utilities Impulse Response](https://doitong.com/developers/models/workflow-utilities/impulse-response.md) (`workflow-utilities/impulse-response`): $0.001 / second of processing time

## Links

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