# Maya1 API

> Teks-ke-pertuturan ekspresif dengan gesaan penerangan suara dan tag emosi sebaris

Menukar teks sehingga 5000 aksara kepada pertuturan. `prompt` wajib sehingga 500 aksara menerangkan suara, seperti umur, loghat dan nada. Tag emosi seperti ketawa atau bisikan boleh disematkan dalam teks. Pilih kadar sampel 48 kHz atau 24 kHz dan output wav atau mp3; `max_tokens` mengehadkan panjang audio.

- Model id: `maya`
- Made by: Maya Research
- Category: Text to Speech
- Output: audio
- Estimated price per run: $0.049 / run (cheapest run $0.049 (49 API credits))
- Run: `POST https://api.doitong.com/v1/run/maya`
- Quote: `POST https://api.doitong.com/v1/quote/maya`
- Docs page: https://doitong.com/ms/developers/models/maya

## Pricing

Price: **$0.049 / run**. Estimated from the typical cost of one run. The quote is exactly what the run charges.

The full example input below costs $0.049 = 49 API credits (1 request × 49 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/maya` 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 |  | ≤ 5000 characters | Teks sintesis pertuturan yang membenarkan tag emosi dalam bentuk <emotion_name> pada mana-mana kedudukan, seperti dalam 'Hello world! <excited> This is amazing!' atau 'I can't believe this <sigh> happened again.'. Emosi yang disokong ialah curious, sarcastic, giggle, gulp, exhale, snort, sing, scream, cry, whisper, excited, angry, gasp, chuckle, sigh, laugh_harder, dan laugh. |
| `prompt` |  | string | yes |  | ≤ 500 characters | Ciri suara atau watak yang hendak dihuraikan, seperti intensiti, nada, kelajuan, timbre, pic, aksen dan umur. |
| `temperature` |  | number | no | `0.4` | 0 – 2 | Suhu pensampelan yang mengawal variasi audio: meningkatkannya menghasilkan lebih banyak kepelbagaian, manakala julat lebih rendah 0.2–0.5 mengutamakan kestabilan dan konsistensi. |
| `top_p` |  | number | no | `0.9` | 0 – 1 | Tetapan pensampelan nukleus yang melaraskan kepelbagaian pemilihan token. |
| `max_tokens` |  | integer | no | `2000` | 28 – 4,000 | Belanjawan token SNAC yang mengehadkan tempoh audio, dikira pada kadar 7 token bagi setiap bingkai. |
| `repetition_penalty` |  | number | no | `1.1` | 1 – 2 | Penalti yang dikenakan pada pengulangan token. Meningkatkannya menekan artifak pengulangan. |
| `sample_rate` |  | enum (string) | no | `48 kHz` | `48 kHz`, `24 kHz` | Pilihan kadar sampel audio antara pemprosesan lebih pantas pada 24 kHz dan output berkualiti lebih tinggi pada 48 kHz. |
| `output_format` |  | enum (string) | no | `wav` | `wav`, `mp3` | Format fail audio yang digunakan untuk pertuturan tersintesis. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Pemeriksaan boleh dilonggarkan dengan menetapkannya kepada false, jika pemanggil dibenarkan. |

## Example input

Required parameters only:

```json
{
  "text": "Hello from Doitong. This is a short test sentence.",
  "prompt": "Hello from Doitong. This is a short test sentence."
}
```

A fuller example:

```json
{
  "text": "Hello from Doitong. This is a short test sentence.",
  "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/maya?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Hello from Doitong. This is a short test sentence.",
    "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/maya?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "text": "Hello from Doitong. This is a short test sentence.",
    "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 = {
    "text": "Hello from Doitong. This is a short test sentence.",
    "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/maya", 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": "maya",
      "input": {
        "text": "Hello from Doitong. This is a short test sentence.",
        "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": "maya",
  "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": 49,
    "usd": "0.049",
    "charged": 49,
    "refunded": 0
  },
  "input": {
    "text": "Hello from Doitong. This is a short test sentence.",
    "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,
    "sample_rate": "48 kHz",
    "generation_time": 2.3,
    "rtf": 0.51
  },
  "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} | Fail pertuturan yang dijana dalam WAV atau MP3, dengan audio mono pada 24 kHz atau 48 kHz seperti yang ditentukan oleh pensampel naik. |
| `duration` | number | Panjang output audio, diukur dalam saat. |
| `sample_rate` | string | Kadar pensampelan output audio. |
| `generation_time` | number | Masa penjanaan audio, diukur dalam saat. |
| `rtf` | number | Faktor masa nyata yang dikira sebagai generation_time dibahagi dengan audio_duration; nilai lebih kecil menunjukkan prestasi lebih baik. |

## Related models

- [Maya · Batch](https://doitong.com/developers/models/maya/batch.md) (`maya/batch`): $0.049 / run
- [Maya · Stream](https://doitong.com/developers/models/maya/stream.md) (`maya/stream`): $0.049 / 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/maya
- 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=maya
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/maya