# Mirelo SFX2.0 · Text to Audio API

> Soundeffekte aus einer Textbeschreibung mit Negativ-Prompt, Dauer und mehreren Samples

Erzeugt aus einem `prompt` mit bis zu 2000 Zeichen Soundeffekte; mit `negative_prompt` können Geräusche ausgeschlossen werden. `duration` reicht von 0.1 bis 600 Sekunden (Standard 30), und `num_samples` erzeugt 1 bis 4 Varianten, jeweils mit eigenem Seed. Das Ausgabeformat ist wav, mp3, aac oder flac über `upload_audio_format`, optional mit einer Bitrate für mp3 und aac.

- 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/de/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 | Beschreibung des gewünschten Soundeffekts. |
| `negative_prompt` |  | string \| null | no |  | ≤ 1000 characters | Sounds, die aus der Ausgabe ausgeschlossen werden sollen. |
| `duration` |  | number | no | `30` | 0.1 – 600 | Angeforderte Soundlänge in Sekunden; sie muss innerhalb des deploymentspezifischen Maximums für text-to-SFX liegen. |
| `seed` |  | integer \| null | no |  | -1 – 9,223,372,036,854,776,000 | Seed des ersten Samples; für -1 oder bei Auslassung wird ein zufälliger Seed verwendet. |
| `num_samples` |  | integer | no | `2` | 1 – 4 | Anzahl der Samples für die Generierung innerhalb eines einzelnen gebündelten Forward-Passes. |
| `upload_audio_format` |  | enum (string) | no | `wav` | `wav`, `mp3`, `aac`, `flac` | Für jede Audiodatei verwendetes Format. |
| `upload_audio_bitrate_kbps` |  | integer \| null | no |  | 32 – 320 | Überschreibung der Upload-Bitrate in kbps; wird abgelehnt, wenn upload_audio_format verlustfrei ist. Ohne Angabe bleiben LAME V0 VBR für mp3 oder ein Zielwert von 256 kbps für aac erhalten. Für mp3 eine exakte konstante Rate aus 32, 40, 48, 56, 64, 80, 96, 112, 128, 160, 192, 224, 256, 320 wählen. Für aac geben Werte von 32 bis 256 ein Encoderziel statt einer garantierten Rate an; Mono- oder sparse Audio kann darunter liegen. |

## 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 | SFX-Modellversion zur Erzeugung der Ausgabe. |
| `audio` | array of object {url, content_type, file_name, file_size} | Generierte Soundeffekte mit einem Ergebnis pro Sample. |
| `seeds` | array of integer | Den Samples entsprechende Seeds in ihrer ursprünglichen Reihenfolge. |

## 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