# ACE Step API

> Compose de la musique à partir de balises de genre et de paroles facultatives, pour une durée de 5 à 240 secondes

Crée une piste musicale à partir de `tags` de style séparées par des virgules et de `lyrics` facultatives. Les marqueurs de section comme [verse] et [chorus] structurent la chanson, et [inst] produit une version instrumentale. `duration` va de 5 à 240 secondes. Les contrôles d'échantillonnage comprennent `scheduler` (euler ou heun), `guidance_type` et `number_of_steps` de 3 à 60.

- Model id: `ace-step`
- Made by: ACE Studio
- Category: Text to Music
- Output: audio
- Price: $0.0002 / second (60 s ≈ $0.012) (cheapest run $0.012 (12 API credits))
- Run: `POST https://api.doitong.com/v1/run/ace-step`
- Quote: `POST https://api.doitong.com/v1/quote/ace-step`
- Docs page: https://doitong.com/fr-CA/developers/models/ace-step

## Pricing

Price: **$0.0002 / second (60 s ≈ $0.012)**. Billed per second of output (`duration`, default 240).

The full example input below costs $0.012 = 12 API credits (60 s × 0.2 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.com/v1/quote/ace-step` 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 |
|---|---|---|---|---|---|---|
| `tags` |  | string | yes |  |  | Balises de style audio fournies sous forme de genres séparés par des virgules, avec `prompt` comme autre façon de les fournir. |
| `lyrics` |  | string | no | `` |  | Paroles chantées, avec les sections organisées à l’aide de commandes comme [verse], [chorus] et [bridge]. Pour un audio sans paroles chantées, omettez cette entrée ou fournissez seulement [inst] ou [instrumental]. |
| `duration` |  | number | no | `60` | 5 – 240 | Durée, en secondes, de l’audio généré. |
| `number_of_steps` |  | integer | no | `27` | 3 – 60 | Nombre d’étapes utilisées pendant la génération audio. |
| `seed` |  | integer \| null | no |  |  | Graine pour une génération reproductible, choisie aléatoirement sauf si vous fournissez une valeur. |
| `scheduler` |  | enum (string) | no | `euler` | `euler`, `heun` | Ordonnanceur utilisé pendant la génération. |
| `guidance_type` |  | enum (string) | no | `apg` | `cfg`, `apg`, `cfg_star` | Type de CFG utilisé pendant la génération. |
| `granularity_scale` |  | integer | no | `10` | -100 – 100 | Échelle de granularité appliquée pendant la génération. L’augmenter peut réduire les artefacts. |
| `guidance_interval` |  | number | no | `0.5` | 0 – 1 | Partie du calendrier de génération qui reçoit des indications : le choix de 0.5 la limite aux étapes allant de 0.25 * infer_steps à 0.75 * infer_steps, laissant le début et la fin sans indications. |
| `guidance_interval_decay` |  | number | no | `0` | 0 – 1 | Décroissance des indications dans l’intervalle de génération : 0.0 désactive la décroissance; sinon, l’échelle diminue sur cet intervalle de guidance_scale à min_guidance_scale. |
| `guidance_scale` |  | number | no | `15` | 0 – 200 | Échelle des indications appliquées pendant la génération. |
| `minimum_guidance_scale` |  | number | no | `3` | 0 – 200 | Échelle minimale des indications atteinte après la décroissance pendant la génération. |
| `tag_guidance_scale` |  | number | no | `5` | 0 – 10 | Échelle des indications de balises appliquées pendant la génération. |
| `lyric_guidance_scale` |  | number | no | `1.5` | 0 – 10 | Échelle des indications de paroles appliquées pendant la génération. |

## Example input

Required parameters only:

```json
{
  "tags": "lofi, hiphop, drum and bass, trap, chill"
}
```

A fuller example:

```json
{
  "tags": "lofi, hiphop, drum and bass, trap, chill"
}
```

## 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/ace-step?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "tags": "lofi, hiphop, drum and bass, trap, chill"
  }'

# 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/ace-step?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "tags": "lofi, hiphop, drum and bass, trap, chill"
  }),
});
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 = {
    "tags": "lofi, hiphop, drum and bass, trap, chill",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/ace-step", 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": "ace-step",
      "input": {
        "tags": "lofi, hiphop, drum and bass, trap, chill"
      },
      "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": "ace-step",
  "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": 12,
    "usd": "0.012",
    "charged": 12,
    "refunded": 0
  },
  "input": {
    "tags": "lofi, hiphop, drum and bass, trap, chill"
  },
  "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
    },
    "seed": 42,
    "tags": "lofi, hiphop, drum and bass, trap, chill",
    "lyrics": "[inst]"
  },
  "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} | Fichier audio produit par la génération. |
| `seed` | integer | Graine aléatoire utilisée pendant la génération. |
| `tags` | string | Balises de genre appliquées pendant la génération. |
| `lyrics` | string | Paroles appliquées pendant la génération. |

## Related models

- [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
- [ACE Step Prompt To Audio](https://doitong.com/developers/models/ace-step/prompt-to-audio.md) (`ace-step/prompt-to-audio`): $0.0002 / second
- [MiniMax Music 3](https://doitong.com/developers/models/minimax/music-3.md) (`minimax/music-3`): $0.002 / second
- [DiffRhythm: Lyrics to Song](https://doitong.com/developers/models/diffrhythm.md) (`diffrhythm`): $0.001 / second
- [Elevenlabs Music](https://doitong.com/developers/models/elevenlabs/music.md) (`elevenlabs/music`): $0.60 / minute of output audio
- [Elevenlabs Music v2](https://doitong.com/developers/models/elevenlabs/music/v2.md) (`elevenlabs/music/v2`): $0.60 / minute of output audio

## Links

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