# Tada API

> Synthèse vocale avec clonage de voix lisant votre texte avec la voix d’un extrait de référence, avec 10 codes de langue

Clone la voix d’un locuteur depuis un extrait de référence (`audio_url`) et lit le texte du `prompt` avec cette voix. L’option `language` accepte en, ar, ch, de, es, fr, it, ja, pl et pt. Pour les références non anglaises, fournissez un `transcript`, car la reconnaissance intégrée fonctionne uniquement en anglais. La vitesse peut être réglée de 0.5 à 2 et la sortie est au format wav ou mp3.

- Model id: `tada/3b/text-to-speech`
- Made by: Open model
- Category: Text to Speech
- Output: audio
- Price: $0.08 / 1000 characters (cheapest run $0.08 (80 API credits))
- Run: `POST https://api.doitong.com/v1/run/tada/3b/text-to-speech`
- Quote: `POST https://api.doitong.com/v1/quote/tada/3b/text-to-speech`
- Docs page: https://doitong.com/fr/developers/models/tada/3b/text-to-speech

## Pricing

Price: **$0.08 / 1000 characters**. Billed per character of `prompt` (the price is per 1000 characters).

The full example input below costs $0.004 = 4 API credits (50 characters × 80 API credits / 1000 characters).

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/tada/3b/text-to-speech` 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 |
|---|---|---|---|---|---|---|
| `audio_url` | `audio` | string (audio URL) | yes |  |  | Source du clonage vocal fournie sous forme d’URL de fichier audio, identifiant le locuteur dont le modèle doit reproduire les caractéristiques vocales. |
| `transcript` |  | string | no | `` |  | Transcription de l’audio de référence, obligatoire pour les enregistrements dans des langues autres que l’anglais ; la transcription automatique est intégrée uniquement pour l’anglais. |
| `prompt` |  | string | yes |  |  | Contenu parlé fourni sous forme de texte ; le locuteur de référence fournit la voix utilisée pour le restituer. |
| `language` |  | enum (string) | no | `en` | `en`, `ar`, `ch`, `de`, `es`, `fr`, `it`, `ja`, `pl`, `pt` | Code de langue d’alignement textuel, qui doit correspondre à la langue de synthèse lors de la génération de parole dans une langue autre que l’anglais. |
| `num_extra_steps` |  | integer | no | `0` | 0 – 50 | Nombre supplémentaire d’étapes autorégressives pour ajouter une prosodie ou un silence final en poursuivant la parole au-delà du texte fourni. |
| `temperature` |  | number | no | `0.6` | ≤ 2, > 0 | Température d’échantillonnage des jetons textuels : l’augmenter accroît la variété de la sortie ; 0 ou une valeur inférieure n’est pas autorisé. |
| `top_p` |  | number | no | `0.9` | 0 – 1 | Réglage d’échantillonnage Top-p (nucleus) utilisé pour générer le texte. |
| `repetition_penalty` |  | number | no | `1.1` | 1 – 2 | Pénalité appliquée à la répétition des jetons lors de la génération de la sortie. |
| `acoustic_cfg_scale` |  | number | no | `1.6` | 0 – 10 | Force du guidage sans classifieur utilisée pour générer les caractéristiques acoustiques. |
| `noise_temperature` |  | number | no | `0.9` | 0 – 2 | Température du bruit utilisée pendant la diffusion par flow matching. |
| `num_inference_steps` |  | integer | no | `20` | 1 – 50 | Nombre d’étapes du solveur ODE utilisé pour générer l’acoustique par flow matching. |
| `speed_up_factor` |  | number | no | `1` | 0.5 – 2 | Multiplicateur de vitesse de la parole : la parole générée est plus lente sous 1.0 et plus rapide au-dessus de 1.0. |
| `output_format` |  | enum (string) | no | `wav` | `wav`, `mp3` | Format de fichier de l’audio généré. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Le filtrage peut être assoupli en définissant false, si l'appelant est autorisé. |

File parameters (`audio`) 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
{
  "audio": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
  "prompt": "Hello from Doitong. This is a short test sentence."
}
```

A fuller example:

```json
{
  "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
  "prompt": "Hello from Doitong. This is a short test sentence."
}
```

## 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/tada/3b/text-to-speech?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
    "prompt": "Hello from Doitong. This is a short test sentence."
  }'

# 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/tada/3b/text-to-speech?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
    "prompt": "Hello from Doitong. This is a short test sentence."
  }),
});
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 = {
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
    "prompt": "Hello from Doitong. This is a short test sentence.",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/tada/3b/text-to-speech", 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": "tada/3b/text-to-speech",
      "input": {
        "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
        "prompt": "Hello from Doitong. This is a short test sentence."
      },
      "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": "tada/3b/text-to-speech",
  "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": 4,
    "usd": "0.004",
    "charged": 4,
    "refunded": 0
  },
  "input": {
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
    "prompt": "Hello from Doitong. This is a short test sentence."
  },
  "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,
      "duration": 5,
      "channels": 1,
      "sample_rate": 1,
      "bitrate": "string"
    }
  },
  "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, duration, channels, sample_rate, bitrate} | Fichier audio contenant la parole synthétisée. |

## Related models

- [Tada TTS 1B](https://doitong.com/developers/models/tada/1b/text-to-speech.md) (`tada/1b/text-to-speech`): $0.05 / 1000 characters
- [Eleven v4 Text to Speech](https://doitong.com/developers/models/elevenlabs/tts/eleven-v4.md) (`elevenlabs/tts/eleven-v4`): $0.08 / 1000 characters
- [MiniMax Speech 2.8 HD](https://doitong.com/developers/models/minimax/speech-2.8-hd.md) (`minimax/speech-2.8-hd`): $0.10 / 1000 characters
- [F5 TTS](https://doitong.com/developers/models/f5-tts.md) (`f5-tts`): $0.05 / 1000 characters
- [Async Text to Speech Pro V1.0](https://doitong.com/developers/models/async/tts-pro/v1.0.md) (`async/tts-pro/v1.0`): $0.01 / 1000 characters
- [Bytedance Seed Speech Text to Speech](https://doitong.com/developers/models/bytedance/seed-speech/tts/v2.md) (`bytedance/seed-speech/tts/v2`): $0.03 / 1000 characters
- [Chatterbox · Speech to Speech](https://doitong.com/developers/models/chatterbox/speech-to-speech.md) (`chatterbox/speech-to-speech`): $0.015 / minute of input audio
- [Chatterbox · Text to Speech](https://doitong.com/developers/models/chatterbox/text-to-speech.md) (`chatterbox/text-to-speech`): $0.025 / 1000 characters

## Links

- HTML page: https://doitong.com/developers/models/tada/3b/text-to-speech
- 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=tada/3b/text-to-speech
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/tada/3b/text-to-speech