# Lyria3 API

> 文字轉音樂模型，可選擇接受圖片營造氛圍，並支援人聲與歌詞

從最多 5000 個字元的文字 `prompt` 創作音樂曲目，可描述類型、情緒、樂器編制、速度與人聲風格。可選的 `image_url` 為情緒與主題提供靈感。結果為 MP3 音訊檔，適用時另含 `lyrics` 文字欄位。不支援負面提示詞。

- Model id: `lyria3`
- Made by: Google
- Category: Text to Music
- Output: audio
- Price: $0.04 / request (cheapest run $0.04 (40 API credits))
- Run: `POST https://api.doitong.ru/v1/run/lyria3`
- Quote: `POST https://api.doitong.ru/v1/quote/lyria3`
- Docs page: https://doitong.com/zh-TW/developers/models/lyria3

## Pricing

Price: **$0.04 / request**. Billed once per request.

The full example input below costs $0.04 = 40 API credits (1 request × 40 API credits).

Prices are the upstream price in USD, paid from the API balance in API credits (1000 API credits = 1 USD). `POST https://api.doitong.ru/v1/quote/lyria3` 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 |
|---|---|---|---|---|---|---|
| `prompt` |  | string | yes |  | 1 – 5000 characters | Lyria 3 的音樂生成提示詞，可生成多種語言的歌聲和歌詞。為取得最佳結果，請描述所需的曲風和情緒，以及配器、節奏和聲樂風格。 |
| `negative_prompt` |  | string | no | `` |  | Lyria 3 不提供負面提示詞功能。 |
| `image_url` | `image` | string (image URL) \| null | no |  |  | 透過圖像 URL 提供的選填音樂靈感；圖像的情緒和主題會引導模型創作音樂。 |
| `enable_safety_checker` |  | boolean | no | `true` |  | 在呼叫端獲得授權的情況下，將此值設為 false 可放寬審核。 |

File parameters (`image`) 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
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}
```

A fuller example:

```json
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}
```

## 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.ru/v1/run/lyria3?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }'

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

### JavaScript

```javascript
const API = "https://api.doitong.ru/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/lyria3?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }),
});
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.ru/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/lyria3", 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.ru/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": "lyria3",
      "input": {
        "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
      },
      "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": "lyria3",
  "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": 40,
    "usd": "0.04",
    "charged": 40,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  },
  "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
    },
    "lyrics": "Caption: This is a high-energy Progressive House anthem, a subgenre of EDM defined by its massive scale and uplifting melodic content, all polished with a clean, powerful, and wide stereo production aesthetic. The rhythmic foundation is a punchy, heavily compressed four-on-the-floor kick drum, modeled after a classic Roland TR-909, providing a relentless pulse at 128 BPM. Supporting the kick are crisp, bright open hi-hats on the off-beats and a thick clap/snare layer on beats 2 and 4. The harmonic and melodic core is built from multiple synth layers: vast, shimmering supersaw synth pads play a soaring major-key chord progression; a powerful, monophonic sawtooth bassline plays the root notes and is aggressively side-chained to the kick drum to create the genre's signature 'pumping' effect. Above it all, a soaring supersaw lead synth—composed of multiple detuned sawtooth waves to create a thick, wide sound—plays a memorable, uplifting arpeggiated melody. A powerful, clean female vocal delivers the catchy hook, processed with significant hall reverb and delay to make it feel enormous and seamlessly blend with the synths. The entire instrumental bed (pads, lead, bass) is also heavily side-chained to the kick, ensuring every element ducks in volume with each beat to maximize the kick's punch and drive the track forward.\nMosic: 4.5\nBPM: 128.0"
  },
  "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.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `audio` | object {url, content_type, file_name, file_size} | MP3 格式的音樂輸出。 |
| `lyrics` | string \| null | 適用時，生成或提供的曲目歌詞。 |

## Related models

- [Lyria 3 Pro](https://doitong.com/developers/models/lyria3/pro.md) (`lyria3/pro`): $0.08 / request
- [MiniMax Music 3](https://doitong.com/developers/models/minimax/music-3.md) (`minimax/music-3`): $0.002 / second
- [Lyria 3.5](https://doitong.com/developers/models/google/lyria-3.5.md) (`google/lyria-3.5`): $0.10 / request
- [Lyria2](https://doitong.com/developers/models/lyria2.md) (`lyria2`): $0.10 / run
- [ACE Step](https://doitong.com/developers/models/ace-step.md) (`ace-step`): $0.0002 / second
- [ACE Step Audio Inpaint](https://doitong.com/developers/models/ace-step/audio-inpaint.md) (`ace-step/audio-inpaint`): $0.0002 / second of input audio
- [ACE Step Audio Outpaint](https://doitong.com/developers/models/ace-step/audio-outpaint.md) (`ace-step/audio-outpaint`): $0.0002 / second of output audio
- [ACE Step Audio To Audio](https://doitong.com/developers/models/ace-step/audio-to-audio.md) (`ace-step/audio-to-audio`): $0.0002 / second of input audio

## Links

- HTML page: https://doitong.com/developers/models/lyria3
- 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=lyria3
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.ru/v1/models/lyria3