# VibeVoice 1.5B API

> Synthèse vocale multi-locuteurs pour les scripts longs tels que les podcasts, avec une voix par locuteur

Convertit un `script` de 90000 caractères maximum en parole. Le dialogue peut utiliser des préfixes « Speaker X: » et la liste `speakers` obligatoire définit les voix. `cfg_scale` va de 1 à 2 et contrôle la fidélité au texte, tandis que `seed` rend les exécutions reproductibles. Renvoie l'audio ainsi que sa durée et sa fréquence d'échantillonnage.

- Model id: `vibevoice`
- Made by: Microsoft
- Category: Text to Speech
- Output: audio
- Estimated price per run: $0.02 / run (cheapest run $0.02 (20 API credits))
- Run: `POST https://api.doitong.ru/v1/run/vibevoice`
- Quote: `POST https://api.doitong.ru/v1/quote/vibevoice`
- Docs page: https://doitong.com/fr-FR/developers/models/vibevoice

## Pricing

Price: **$0.02 / run**. Estimated from the typical cost of one run. The quote is exactly what the run charges.

The full example input below costs $0.02 = 20 API credits (1 request × 20 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.ru/v1/quote/vibevoice` 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 |
|---|---|---|---|---|---|---|
| `script` |  | string | yes |  | ≤ 90000 characters | Script d’entrée vocale, avec des libellés facultatifs 'Speaker X:' pour distinguer les locuteurs dans un dialogue. |
| `speakers` |  | array of object {preset, audio_url} | yes |  |  | Les locuteurs sont déduits automatiquement à partir du script ou des échantillons vocaux fournis ; fournissez une liste pour les spécifier explicitement. |
| `speakers[].preset` |  | enum (string) | no | `Alice [EN]` | `Alice [EN]`, `Carter [EN]`, `Frank [EN]`, `Mary [EN] (Background Music)`, `Maya [EN]`, `Anchen [ZH] (Background Music)`, `Bowen [ZH]`, `Xinran [ZH]` | Préréglage vocal de secours pour un locuteur sans `audio_url` ; la fourniture de cet échantillon audio est prioritaire sur le préréglage. |
| `speakers[].audio_url` |  | string (audio URL) \| null | no |  |  | URL du fichier audio d’échantillon vocal ; sa fourniture remplace `preset`. |
| `seed` |  | integer \| null | no |  |  | Seed aléatoire rendant la génération reproductible. |
| `cfg_scale` |  | number | no | `1.3` | 1 – 2 | La puissance CFG (Classifier-Free Guidance) détermine à quel point la génération suit le texte ; l’adhérence augmente avec des valeurs plus élevées. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Le filtrage peut être assoupli en définissant false, si l'appelant est autorisé. |

## Example input

Required parameters only:

```json
{
  "script": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
  "speakers": [
    {
      "preset": "Frank [EN]"
    },
    {
      "preset": "Carter [EN]"
    }
  ]
}
```

A fuller example:

```json
{
  "script": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
  "speakers": [
    {
      "preset": "Frank [EN]"
    },
    {
      "preset": "Carter [EN]"
    }
  ]
}
```

## 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/vibevoice?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "script": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "speakers": [
      {
        "preset": "Frank [EN]"
      },
      {
        "preset": "Carter [EN]"
      }
    ]
  }'

# 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/vibevoice?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "script": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "speakers": [
      {
        "preset": "Frank [EN]"
      },
      {
        "preset": "Carter [EN]"
      }
    ]
  }),
});
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 = {
    "script": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "speakers": [
        {
            "preset": "Frank [EN]",
        },
        {
            "preset": "Carter [EN]",
        },
    ],
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/vibevoice", 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": "vibevoice",
      "input": {
        "script": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
        "speakers": [
          {
            "preset": "Frank [EN]"
          },
          {
            "preset": "Carter [EN]"
          }
        ]
      },
      "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": "vibevoice",
  "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": 20,
    "usd": "0.02",
    "charged": 20,
    "refunded": 0
  },
  "input": {
    "script": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "speakers": [
      {
        "preset": "Frank [EN]"
      },
      {
        "preset": "Carter [EN]"
      }
    ]
  },
  "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,
    "sample_rate": 24000,
    "generation_time": 5.6,
    "rtf": 0.53
  },
  "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 contenant la parole synthétisée. |
| `duration` | number | Durée de la sortie audio, mesurée en secondes. |
| `sample_rate` | integer | Fréquence d'échantillonnage de la sortie audio. |
| `generation_time` | number | Temps de génération audio, mesuré en secondes. |
| `rtf` | number | Facteur temps réel calculé comme generation_time divisé par audio_duration ; des valeurs plus faibles indiquent de meilleures performances. |

## Related models

- [Vibevoice](https://doitong.com/developers/models/vibevoice/0.5b.md) (`vibevoice/0.5b`): $0.01 / run
- [VibeVoice 7B](https://doitong.com/developers/models/vibevoice/7b.md) (`vibevoice/7b`): $0.04 / run
- [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
- [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/vibevoice
- 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=vibevoice
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.ru/v1/models/vibevoice