# Eleven v4 Text to Speech API

> Le modèle vocal le plus expressif d’ElevenLabs, avec balises d’émotion intégrées et horodatages des mots.

Eleven v4 lit le texte à voix haute avec des voix naturelles et expressives et comprend les balises audio intégrées comme [excited] ou [whispering], ainsi que les prononciations IPA. Choisissez une voix, ajustez la stabilité et la similarité, définissez la langue, et obtenez facultativement les horodatages au niveau des mots. Formats MP3, PCM, Opus et téléphonie.

- Model id: `elevenlabs/tts/eleven-v4`
- Made by: ElevenLabs
- Category: Text to Speech
- Output: audio
- Price: $0.08 / 1000 characters (cheapest run $0.08 (80 API credits))
- Run: `POST https://api.doitong.ru/v1/run/elevenlabs/tts/eleven-v4`
- Quote: `POST https://api.doitong.ru/v1/quote/elevenlabs/tts/eleven-v4`
- Docs page: https://doitong.com/fr-CA/developers/models/elevenlabs/tts/eleven-v4

## Pricing

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

The full example input below costs $0.004 = 4 API credits (48 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.ru/v1/quote/elevenlabs/tts/eleven-v4` 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 |
|---|---|---|---|---|---|---|
| `text` |  | string | yes |  | 1 – 5000 characters | Fournissez le contenu vocal sous forme de texte, en indiquant facultativement le rendu avec des balises audio comme [whispering] ou les prononciations IPA entre des barres obliques. |
| `voice` |  | string | no | `Rachel` |  | Voix sélectionnée pour synthétiser la parole. |
| `stability` |  | number | no | `0.5` | 0 – 1 | La stabilité de la voix équilibre un rendu expressif avec des valeurs faibles et un rendu constant avec des valeurs élevées. |
| `similarity_boost` |  | number | no | `0.75` | 0 – 1 | Contrôle de la similarité avec la voix de référence, avec un compromis possible sur le naturel : l'augmenter renforce la correspondance, mais peut rendre la sortie moins naturelle. |
| `seed` |  | integer \| null | no |  | 0 – 4,294,967,295 | Graine utilisée pour tenter d'obtenir des résultats reproductibles; la répétition exacte de la sortie n'est pas garantie. |
| `language_code` |  | string \| null | no |  |  | Code de langue ISO 639-1 utilisé pour générer la parole et normaliser le texte. |
| `output_format` |  | enum (string) | no | `mp3_44100_128` | `mp3_22050_32`, `mp3_44100_32`, `mp3_44100_64`, `mp3_44100_96`, `mp3_44100_128`, `mp3_44100_192`, `pcm_8000`, `pcm_16000`, `pcm_22050`, `pcm_24000`, `pcm_44100`, `pcm_48000`, `ulaw_8000`, `alaw_8000`, `opus_48000_32`, `opus_48000_64`, `opus_48000_96`, `opus_48000_128`, `opus_48000_192` | Format audio généré, spécifié selon le modèle codec_sample_rate_bitrate. |
| `apply_text_normalization` |  | enum (string) | no | `auto` | `auto`, `on`, `off` | Contrôle la normalisation du texte avant la génération, notamment le traitement des nombres et des dates. |
| `timestamps` |  | boolean | no | `false` |  | Contrôle si l'audio généré est accompagné de données de synchronisation pour chaque caractère. |

## Example input

Required parameters only:

```json
{
  "text": "[excited] Hello! Welcome to the future of voice."
}
```

A fuller example:

```json
{
  "text": "[excited] Hello! Welcome to the future of voice.",
  "voice": "Aria"
}
```

## 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/elevenlabs/tts/eleven-v4?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "[excited] Hello! Welcome to the future of voice.",
    "voice": "Aria"
  }'

# 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/elevenlabs/tts/eleven-v4?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "text": "[excited] Hello! Welcome to the future of voice.",
    "voice": "Aria"
  }),
});
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 = {
    "text": "[excited] Hello! Welcome to the future of voice.",
    "voice": "Aria",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/elevenlabs/tts/eleven-v4", 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": "elevenlabs/tts/eleven-v4",
      "input": {
        "text": "[excited] Hello! Welcome to the future of voice.",
        "voice": "Aria"
      },
      "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": "elevenlabs/tts/eleven-v4",
  "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": {
    "text": "[excited] Hello! Welcome to the future of voice.",
    "voice": "Aria"
  },
  "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
    },
    "timestamps": []
  },
  "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 |
|---|---|---|
| `audio` | object {url, content_type, file_name, file_size} | Fichier audio produit par la génération. |
| `timestamps` | array of any \| null | Données temporelles de la parole générée, incluses uniquement pour les requêtes dont `timestamps` est défini sur True, avec un horodatage pour chaque mot. |

## Related models

- [Eleven v4 Turbo](https://doitong.com/developers/models/elevenlabs/tts/eleven-v4-turbo.md) (`elevenlabs/tts/eleven-v4-turbo`): $0.04 / 1000 characters
- [Elevenlabs Tts Eleven V3](https://doitong.com/developers/models/elevenlabs/tts/eleven-v3.md) (`elevenlabs/tts/eleven-v3`): $0.10 / 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
- [Elevenlabs](https://doitong.com/developers/models/elevenlabs/text-to-dialogue/eleven-v3.md) (`elevenlabs/text-to-dialogue/eleven-v3`): $0.10 / run
- [ElevenLabs TTS Multilingual v2](https://doitong.com/developers/models/elevenlabs/tts/multilingual-v2.md) (`elevenlabs/tts/multilingual-v2`): $0.10 / 1000 characters
- [ElevenLabs TTS Turbo v2.5](https://doitong.com/developers/models/elevenlabs/tts/turbo-v2.5.md) (`elevenlabs/tts/turbo-v2.5`): $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

## Links

- HTML page: https://doitong.com/developers/models/elevenlabs/tts/eleven-v4
- 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=elevenlabs/tts/eleven-v4
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.ru/v1/models/elevenlabs/tts/eleven-v4