# Stable Audio 3 Trainer API

> Entraîne un LoRA sur Stable Audio 3 à partir d’une archive zip de clips audio accompagnés de légendes textuelles correspondantes

Effectue un ajustement fin d’un point de contrôle de base (medium-base, small-music-base ou small-sfx-base) sur une archive zip `audio_data_url`, où chaque fichier audio possède une légende `.txt` portant le même nom. Vous pouvez régler `number_of_steps` (jusqu’à 20000), `learning_rate`, `rank` (de 1 à 256), `adapter_type` et `batch_size`, ou reprendre depuis un point de contrôle `.safetensors`. Renvoie les poids LoRA et un fichier de configuration.

- Model id: `stable-audio-3-trainer`
- Made by: Stability AI
- Category: Training
- Output: file
- Price per run: from $0.003 / run (cheapest run $0.003 (3 API credits))
- Run: `POST https://api.doitong.ru/v1/run/stable-audio-3-trainer`
- Quote: `POST https://api.doitong.ru/v1/quote/stable-audio-3-trainer`
- Docs page: https://doitong.com/fr/developers/models/stable-audio-3-trainer

## Pricing

Price: **from $0.003 / run** (the lowest tier; the quote prices your exact input). Price per run: 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 $3.00 = 3000 API credits (1 run × $3.00).

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/stable-audio-3-trainer` 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 |
|---|---|---|---|---|---|---|
| `audio_data_url` |  | string | yes |  |  | URL du fichier zip du jeu de données, chaque paire audio/légende étant stockée ensemble avec des noms de base correspondants : `clip.wav` correspond par exemple à `clip.txt`. Les légendes doivent utiliser l’extension `.txt`. |
| `model` |  | enum (string) | no | `medium-base` | `medium-base`, `small-music-base`, `small-sfx-base` | Point de contrôle de base pour le fine-tuning de Stable Audio 3. |
| `number_of_steps` |  | integer | no | `1000` | 1 – 20,000 | Nombre d'étapes pour l'entraînement LoRA. |
| `learning_rate` |  | number | no | `0.0001` | ≤ 0.01, > 0 | Taux d’apprentissage appliqué par AdamW aux paramètres LoRA. |
| `rank` |  | integer | no | `16` | 1 – 256 | Rang de l’adaptateur LoRA. |
| `adapter_type` |  | enum (string) | no | `dora-rows` | `lora`, `dora`, `dora-rows`, `dora-cols`, `bora`, `lora-xs`, `dora-rows-xs`, `dora-cols-xs`, `bora-xs` | Famille d’adaptateur utilisée pour l’entraînement LoRA. |
| `duration` |  | number \| null | no |  | 1 – 380 | Durée de recadrage et de remplissage en secondes, limitée dans tous les cas par la longueur d’entraînement native du modèle sélectionné. Fournissez une durée ou omettez-la pour utiliser le clip le plus long détecté dans le jeu de données, dans la limite autorisée. |
| `batch_size` |  | integer | no | `1` | 1 – 8 | Taille de lot utilisée pendant l’entraînement. |
| `seed` |  | integer | no | `42` | 0 – 2,147,483,647 | Graine de la randomisation. |
| `base_precision` |  | enum (string) | no | `bf16` | `bf16`, `bfloat16`, `fp16`, `float16` | Précision utilisée par les poids de base gelés ; les paramètres LoRA restent en fp32. |
| `include` |  | array of string \| null | no |  |  | Sous-chaînes de noms de modules qui limitent les emplacements où LoRA est ajouté : seuls les modules correspondants le reçoivent. |
| `exclude` |  | array of string \| null | no |  |  | Sous-chaînes de noms utilisées pour exclure les modules correspondants. |
| `lora_checkpoint_url` |  | string \| null | no |  |  | URL facultative d’un point de contrôle LoRA `.safetensors` à partir duquel reprendre l’entraînement. |
| `pre_encode` |  | boolean | no | `false` |  | Pré-encodage de l’archive audio en latents SAME avant l’entraînement de LoRA. |

## Example input

Required parameters only:

```json
{
  "audio_data_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
}
```

A fuller example:

```json
{
  "audio_data_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.ru/v1/run/stable-audio-3-trainer?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "audio_data_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.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/stable-audio-3-trainer?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "audio_data_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.ru/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "audio_data_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/stable-audio-3-trainer", 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": "stable-audio-3-trainer",
      "input": {
        "audio_data_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": "stable-audio-3-trainer",
  "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": 3000,
    "usd": "3.00",
    "charged": 3000,
    "refunded": 0
  },
  "input": {
    "audio_data_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  },
  "output": {
    "lora_file": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    },
    "config_file": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    }
  },
  "outputs": [
    {
      "type": "file",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_size": 1843200,
      "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 |
|---|---|---|
| `lora_file` | object {url, content_type, file_name, file_size} | Poids LoRA entraînés pour Stable Audio 3. |
| `config_file` | object {url, content_type, file_name, file_size} | Métadonnées JSON décrivant l’exécution d’entraînement et le modèle compatible pour l’inférence. |

## Related models

- [ERNIE-Image Trainer](https://doitong.com/developers/models/ernie-image-trainer.md) (`ernie-image-trainer`): $0.0012 / step
- [FLUX 2 \[klein\] 9b Base Trainer](https://doitong.com/developers/models/flux-2-klein-9b-base-trainer.md) (`flux-2-klein-9b-base-trainer`): $0.0043 / step
- [Flux 2 Klein 9B Base Trainer](https://doitong.com/developers/models/flux-2-klein-9b-base-trainer/edit.md) (`flux-2-klein-9b-base-trainer/edit`): $0.0139 / step
- [FLUX 2 Trainer](https://doitong.com/developers/models/flux-2-trainer.md) (`flux-2-trainer`): $0.0064 / step
- [FLUX 2 Trainer Edit](https://doitong.com/developers/models/flux-2-trainer/edit.md) (`flux-2-trainer/edit`): $0.0389 / step
- [FLUX 2 Trainer V2](https://doitong.com/developers/models/flux-2-trainer-v2.md) (`flux-2-trainer-v2`): $0.0064 / step
- [FLUX 2 Trainer V2 Edit](https://doitong.com/developers/models/flux-2-trainer-v2/edit.md) (`flux-2-trainer-v2/edit`): $0.0389 / step
- [Flux Kontext Trainer](https://doitong.com/developers/models/flux-kontext-trainer.md) (`flux-kontext-trainer`): from $1.25 / run

## Links

- HTML page: https://doitong.com/developers/models/stable-audio-3-trainer
- 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=stable-audio-3-trainer
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.ru/v1/models/stable-audio-3-trainer