# Async Text to Speech Pro V1.0 API

> Chuyển văn bản thành giọng nói với lựa chọn giọng, tùy chọn nhân bản giọng và sáu tùy chọn ngôn ngữ bắt buộc

Chuyển `transcript` thành lời nói bằng đối tượng `voice` được chọn. Tham số `language` tùy chọn buộc tổng hợp bằng English, French, Spanish, German, Italian hoặc Portuguese. Đối tượng `output_format` cấu hình âm thanh, còn kết quả gồm tệp âm thanh, loại MIME và kích thước tính bằng byte. Phù hợp cho thuyết minh khi cần chọn một giọng cụ thể.

- Model id: `async/tts-pro/v1.0`
- Made by: Async
- Category: Text to Speech
- Output: audio
- Price: $0.01 / 1000 characters (cheapest run $0.01 (10 API credits))
- Run: `POST https://api.doitong.com/v1/run/async/tts-pro/v1.0`
- Quote: `POST https://api.doitong.com/v1/quote/async/tts-pro/v1.0`
- Docs page: https://doitong.com/vi/developers/models/async/tts-pro/v1.0

## Pricing

Price: **$0.01 / 1000 characters**. Billed per character of `transcript` (the price is per 1000 characters).

The full example input below costs $0.001 = 1 API credit (50 characters × 10 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/async/tts-pro/v1.0` 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 |
|---|---|---|---|---|---|---|
| `transcript` |  | string | yes |  |  | Nội dung văn bản cần tổng hợp thành lời nói. |
| `voice` |  | object {name} | yes |  |  | Giọng nói được chọn để tổng hợp lời nói. |
| `voice.name` |  | enum (string) | no | `Jennie` | `Jennie`, `Stella`, `Max`, `Hayes`, `Elara`, `Cleo`, `Fisher`, `Corin`, `Thaddeus`, `Lucina`, `Acadia`, `Huxley`, `Winslet`, `Jethro`, `Elio`, `Rupert`, `Eira`, `Nyra`, `Arian`, `Lily`, `Pierce`, `Kaela`, `Elowen`, `Freya`, `Lenny`, `Alessa`, `Pandora`, `Fia`, `Abbott`, `Kael`, `Orla`, `Sable`, `Marnie`, `Sera`, `Virel`, `Liora`, `Riven`, `Elys`, `Dreena`, `Rhea`, `Vela`, `Nymera`, `Isolde`, `Lirien`, `Zella`, `Avenna`, `Mirelle`, `Calia`, `Lunea`, `Lucan`, `Tarian`, `Arlo`, `Jovan`, `Neron`, `Ziven`, `Dax`, `Orien`, `Lior`, `Eryx`, `Tyren`, `Nox`, `Elric`, `Varian`, `Zoran`, `Miro`, `Dalen`, `Ronix`, `Jarek`, `Nyxie`, `Soren`, `Viona`, `Selene`, `Rachiel`, `Corbin`, `Abigail`, `Faith`, `Kimberly`, `Dave`, `Grace`, `Alden`, `Renly`, `Violet`, `Joel`, `Xavier`, `Esmeralda`, `Robert`, `Lila`, `Brooks`, `Lennox`, `Vanessa`, `Simon`, `Nyomi`, `Jack`, `Penelope`, `Brayden`, `Abel`, `Nellie`, `Connie`, `Andrew`, `Lincoln` | Giọng nói cài sẵn có tên cần sử dụng. Không có tác dụng nếu `id` được cung cấp. |
| `output_format` |  | object {container, encoding, sample_rate, bit_rate} | no |  |  | Cấu hình cho âm thanh được tạo sinh. |
| `output_format.container` |  | enum (string) | no | `mp3` | `mp3`, `raw` | Định dạng container cho âm thanh được tạo sinh. |
| `output_format.encoding` |  | enum (string) \| null | no |  | `pcm_s16le`, `pcm_f32le`, `pcm_mulaw` | Mã hóa PCM chỉ được áp dụng khi container là 'raw'. |
| `output_format.sample_rate` |  | integer | no | `44100` | 8,000 – 48,000 | Tần số lấy mẫu của đầu ra, tính bằng Hz. |
| `output_format.bit_rate` |  | integer \| null | no |  | 32,000 – 320,000 | Tốc độ bit của đầu ra; chỉ áp dụng cho container 'mp3'. |
| `language` |  | enum (string) \| null | no |  | `en`, `fr`, `es`, `de`, `it`, `pt` | Ngôn ngữ bắt buộc trong quá trình tổng hợp, được chỉ định bằng ISO 639-1. |

## Example input

Required parameters only:

```json
{
  "transcript": "Hello from Doitong. This is a short test sentence.",
  "voice": {
    "name": "Jennie"
  }
}
```

A fuller example:

```json
{
  "transcript": "Hello from Doitong. This is a short test sentence.",
  "voice": {
    "name": "Jennie"
  }
}
```

## 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/async/tts-pro/v1.0?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "transcript": "Hello from Doitong. This is a short test sentence.",
    "voice": {
      "name": "Jennie"
    }
  }'

# 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/async/tts-pro/v1.0?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "transcript": "Hello from Doitong. This is a short test sentence.",
    "voice": {
      "name": "Jennie"
    }
  }),
});
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 = {
    "transcript": "Hello from Doitong. This is a short test sentence.",
    "voice": {
        "name": "Jennie",
    },
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/async/tts-pro/v1.0", 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": "async/tts-pro/v1.0",
      "input": {
        "transcript": "Hello from Doitong. This is a short test sentence.",
        "voice": {
          "name": "Jennie"
        }
      },
      "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": "async/tts-pro/v1.0",
  "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": 1,
    "usd": "0.001",
    "charged": 1,
    "refunded": 0
  },
  "input": {
    "transcript": "Hello from Doitong. This is a short test sentence.",
    "voice": {
      "name": "Jennie"
    }
  },
  "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
    },
    "content_type": "audio/mpeg",
    "size_bytes": 1
  },
  "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} |  |
| `content_type` | string | Loại MIME của âm thanh. |
| `size_bytes` | integer | Kích thước âm thanh tính bằng byte. |

## Related models

- [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
- [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
- [Chatterbox · Text to Speech · Multilingual](https://doitong.com/developers/models/chatterbox/text-to-speech/multilingual.md) (`chatterbox/text-to-speech/multilingual`): $0.025 / 1000 characters
- [Chatterboxhd · Speech to Speech](https://doitong.com/developers/models/resemble-ai/chatterboxhd/speech-to-speech.md) (`resemble-ai/chatterboxhd/speech-to-speech`): $0.02 / minute of input audio
- [Chatterboxhd · Text to Speech](https://doitong.com/developers/models/resemble-ai/chatterboxhd/text-to-speech.md) (`resemble-ai/chatterboxhd/text-to-speech`): $0.0108 / run

## Links

- HTML page: https://doitong.com/developers/models/async/tts-pro/v1.0
- 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=async/tts-pro/v1.0
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/async/tts-pro/v1.0