# Mirelo SFX2.0 · Text to Audio API

> 根据文本描述生成音效，支持负面提示词、时长和多个样本

根据最多 2000 个字符的 `prompt` 生成音效，并使用 `negative_prompt` 排除声音。`duration` 范围为 0.1 到 600 秒（默认 30），`num_samples` 可生成 1 到 4 个变体，每个变体都有自己的种子。通过 `upload_audio_format` 选择 wav、mp3、aac 或 flac 输出格式，mp3 和 aac 还可选比特率。

- Model id: `mirelo-ai/sfx2.0/text-to-audio`
- Made by: Mirelo AI
- Category: Audio
- Output: audio
- Price per second of your output audio: $0.01 / second of output audio (cheapest run $0.01 (10 API credits))
- Run: `POST https://api.doitong.ru/v1/run/mirelo-ai/sfx2.0/text-to-audio`
- Quote: `POST https://api.doitong.ru/v1/quote/mirelo-ai/sfx2.0/text-to-audio`
- Docs page: https://doitong.com/zh/developers/models/mirelo-ai/sfx2.0/text-to-audio

## Pricing

Price: **$0.01 / second of output audio**. Price per second of your output 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 $0.60 = 600 API credits (60 s output audio × $0.01).

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/mirelo-ai/sfx2.0/text-to-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

| Parameter | Canonical name | Type | Required | Default | Allowed values / range | Description |
|---|---|---|---|---|---|---|
| `prompt` |  | string | yes |  | 1 – 2000 characters | 所需音效的描述。 |
| `negative_prompt` |  | string \| null | no |  | ≤ 1000 characters | 要从输出中排除的声音。 |
| `duration` |  | number | no | `30` | 0.1 – 600 | 请求的声音长度，以秒为单位，必须符合特定部署对文本转 SFX 的最大值。 |
| `seed` |  | integer \| null | no |  | -1 – 9,223,372,036,854,776,000 | 初始样本的种子；使用 -1 或省略时会使用随机种子。 |
| `num_samples` |  | integer | no | `2` | 1 – 4 | 单次批量前向传递中用于生成的样本数量。 |
| `upload_audio_format` |  | enum (string) | no | `wav` | `wav`, `mp3`, `aac`, `flac` | 每个音频文件使用的格式。 |
| `upload_audio_bitrate_kbps` |  | integer \| null | no |  | 32 – 320 | 上传比特率覆盖值，单位为 kbps；当 upload_audio_format 为无损格式时会被拒绝。未设置时，mp3 保留 LAME V0 VBR，aac 使用 256 kbps 目标值。对于 mp3，请从 32、40、48、56、64、80、96、112、128、160、192、224、256、320 中选择精确的恒定速率。对于 aac，32 到 256 的值指定编码器目标而非保证速率，因此单声道或稀疏音频可能低于该值。 |

## 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/mirelo-ai/sfx2.0/text-to-audio?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/mirelo-ai/sfx2.0/text-to-audio?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/mirelo-ai/sfx2.0/text-to-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.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": "mirelo-ai/sfx2.0/text-to-audio",
      "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": "mirelo-ai/sfx2.0/text-to-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": 600,
    "usd": "0.60",
    "charged": 600,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  },
  "output": {
    "model": "sfx-2.0",
    "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
      }
    ],
    "seeds": [
      42
    ]
  },
  "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 |
|---|---|---|
| `model` | string | 用于生成输出的 SFX 模型版本。 |
| `audio` | array of object {url, content_type, file_name, file_size} | 生成的音效，每个样本对应一个结果。 |
| `seeds` | array of integer | 与样本对应的种子，保持原有顺序。 |

## Related models

- [Mirelo SFX2.0 · Video to Video](https://doitong.com/developers/models/mirelo-ai/sfx2.0/video-to-video.md) (`mirelo-ai/sfx2.0/video-to-video`): $0.01 / second of output audio
- [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
- [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
- [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/mirelo-ai/sfx2.0/text-to-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=mirelo-ai/sfx2.0/text-to-audio
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.ru/v1/models/mirelo-ai/sfx2.0/text-to-audio