# Grok Voice · Realtime API

> Varian masa nyata ejen suara Grok untuk penstriman dan perbualan audio serta teks dua hala

Ejen suara untuk aplikasi langsung seperti pembantu dan ejen telefon, dibina berasaskan penstriman audio dan teks dalam kedua-dua arah. Inputnya sepadan dengan model suara standard: `audio_url` untuk pertuturan pengguna, arahan persona `prompt` pilihan, pilihan `voice` dan `tools` pilihan untuk akses web, X atau MCP. Ia mengembalikan audio WAV pertuturan, tempohnya dan transkrip.

- Model id: `xai/grok-voice/realtime`
- Made by: xAI
- Category: Audio
- Output: audio
- Charged by usage (up to $1.494 per run, typical $0.006; the rest of the hold is refunded): $0.00083 / second of the voice session (cheapest run $0.006 (6 API credits))
- Run: `POST https://api.doitong.com/v1/run/xai/grok-voice/realtime`
- Quote: `POST https://api.doitong.com/v1/quote/xai/grok-voice/realtime`
- Docs page: https://doitong.com/ms/developers/models/xai/grok-voice/realtime

## Pricing

Price: **$0.00083 / second of the voice session**. Charged by actual usage at $0.00083 / second of the voice session: up to $1.494 per run (the quote gives the maximum for your input), the rest is refunded automatically after the run. A typical run costs $0.006.

The full example input below holds up to $1.494 = 1494 API credits (up to 1800 s of voice session × $0.00083) when it starts; a typical run costs $0.006 (6 API credits).

Prices are the upstream price in USD, paid from the API balance in API credits (1000 API credits = 1 USD). This model is charged by usage: `POST https://api.doitong.com/v1/quote/xai/grok-voice/realtime` with the same JSON body returns the most the run can cost for that input (`credits`, debited when the run starts); after the run you pay the usage the model reports and the rest is refunded automatically. An input whose maximum would exceed the per-run limit is refused with 422. 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 |  |  | URL audio untuk pertuturan pengguna, terhad kepada 10 minit dan 50 MB. Kebanyakan format audio biasa boleh dibekalkan; sebelum Grok menerima audio, ia ditukar kepada PCM mono dengan sampel 16-bit pada 24 kHz. Ejen membalas rakaman tersebut dengan pertuturan. |
| `prompt` |  | string \| null | no |  | ≤ 20000 characters | Arahan sistem pilihan yang membekalkan konteks perbualan dan menentukan persona sebagai ganti persona lalai Grok; jika digugurkan, persona lalai dikekalkan. |
| `voice` |  | enum (string) \| null | no |  | `carina`, `zagan`, `helix`, `orion`, `luna`, `iris`, `altair`, `zenith`, `perseus`, `helios`, `lux`, `kepler`, `rigel`, `cosmo`, `celeste`, `ursa`, `sirius`, `lumen`, `castor`, `naksh`, `atlas`, `aurora`, `liora`, `ara`, `eve`, `leo`, `rex`, `sal` | Pilih suara xAI terbina dalam untuk menggantikan suara lalai Grok bagi balasan ejen; jika tidak ditetapkan, suara lalai dikekalkan. |
| `tools` |  | object {mcp_servers, web_search, x_search} | no | `{"mcp_servers":[],"web_search":{"enabled":false},"x_search":{"enabled":false}}` |  | Konfigurasi alat ejen untuk kegunaan sisi pelayan, tidak termasuk file_search/collections daripada konfigurasi ditaip kerana ZDR. Semua alat bermula dalam keadaan dinyahdayakan; pilihan yang disokong termasuk alat MCP jauh, alat web dan alat X. |
| `tools.mcp_servers` |  | array of object {allowed_tools, authorization, enabled, headers, server_description, server_label, server_url} | no |  |  | Pelayan MCP jauh yang disambungkan oleh penyedia model untuk pelaksanaan alat. |
| `tools.mcp_servers[].allowed_tools` |  | array of string \| null | no |  | ≥ 1 items | Senarai pilihan yang menentukan nama alat yang didedahkan oleh pelayan ini. |
| `tools.mcp_servers[].authorization` |  | string \| null | no |  |  | Nilai kebenaran sensitif yang dihantar secara eksklusif kepada penyedia model. |
| `tools.mcp_servers[].enabled` |  | boolean | no | `true` |  | Bendera penyertaan pelayan; false mengecualikan pelayan. |
| `tools.mcp_servers[].headers` |  | object \| null | no |  |  | Pengepala sensitif untuk permintaan MCP, dihantar secara eksklusif kepada penyedia model. |
| `tools.mcp_servers[].server_description` |  | string \| null | no |  | ≤ 2000 characters | Perihalan yang menggariskan keupayaan yang disediakan oleh pelayan ini. |
| `tools.mcp_servers[].server_label` |  | string | yes |  | 1 – 128 characters | Label pelayan yang digunakan oleh penyedia model untuk mengenal pasti alatnya dan menjadi awalan nama alat tersebut. |
| `tools.mcp_servers[].server_url` |  | string | yes |  | ≥ 1 characters | Alamat HTTP(S) yang dibekalkan oleh pemanggil untuk pelayan MCP yang disambungkan Grok dari jauh melalui pengangkutan Streaming HTTP/SSE. |
| `tools.web_search` |  | object {allowed_domains, enable_image_understanding, enabled, excluded_domains, location} | no | `{"allowed_domains":null,"enable_image_understanding":null,"enabled":false,"excluded_domains":null,"location":null}` |  | Carian web terurus penyedia, dinyahdayakan melainkan enabled ialah true. |
| `tools.web_search.allowed_domains` |  | array of string \| null | no |  | 1 – 5 items | Sekatan domain untuk hasil carian: tentukan sehingga lima domain, tanpa protokol dan laluan. |
| `tools.web_search.enable_image_understanding` |  | boolean \| null | no |  |  | Kebenaran untuk ejen memeriksa imej yang ditemui melalui carian web. |
| `tools.web_search.enabled` |  | boolean | no | `false` |  | Akses carian web untuk ejen: true menambah web_search pada session.tools dan membenarkan carian web; lalai membiarkannya dinyahdayakan. |
| `tools.web_search.excluded_domains` |  | array of string \| null | no |  | 1 – 5 items | Domain yang perlu dikecualikan daripada hasil carian, terhad kepada lima entri tanpa protokol dan laluan. |
| `tools.web_search.location` |  | object {city, country, region, timezone} \| null | no |  |  | Lokasi pilihan untuk menyesuaikan hasil carian mengikut geografi. |
| `tools.x_search` |  | object {allowed_x_handles, enable_image_understanding, enable_video_understanding, enabled, excluded_x_handles, from_date, to_date} | no | `{"allowed_x_handles":null,"enable_image_understanding":null,"enable_video_understanding":null,"enabled":false,"excluded_x_handles":null,"from_date":null,"to_date":null}` |  | Carian X terurus penyedia, dinyahdayakan melainkan enabled ialah true. |
| `tools.x_search.allowed_x_handles` |  | array of string \| null | no |  | 1 – 20 items | Pemegang X yang siarannya mungkin muncul dalam hasil, terhad kepada 20 pemegang. |
| `tools.x_search.enable_image_understanding` |  | boolean \| null | no |  |  | Kebenaran untuk ejen memeriksa imej yang ditemui di X. |
| `tools.x_search.enable_video_understanding` |  | boolean \| null | no |  |  | Kebenaran untuk ejen memeriksa video yang ditemui di X. |
| `tools.x_search.enabled` |  | boolean | no | `false` |  | Akses kepada siaran X melalui carian: true menambah x_search pada session.tools supaya ejen boleh mencari siaran tersebut; lalai membiarkannya dinyahdayakan. |
| `tools.x_search.excluded_x_handles` |  | array of string \| null | no |  | 1 – 20 items | Pemegang X yang siarannya dikecualikan, terhad kepada 20 pemegang. |
| `tools.x_search.from_date` |  | string \| null | no |  |  | Tarikh paling awal untuk siaran, dinyatakan dalam format ISO YYYY-MM-DD. |
| `tools.x_search.to_date` |  | string \| null | no |  |  | Tarikh paling lewat untuk siaran, dinyatakan dalam format ISO YYYY-MM-DD. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Pemeriksaan boleh dilonggarkan dengan menetapkannya kepada false, jika pemanggil dibenarkan. |

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"
}
```

A fuller example:

```json
{
  "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
}
```

## 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/xai/grok-voice/realtime?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"
  }'

# 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/xai/grok-voice/realtime?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  }),
});
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",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/xai/grok-voice/realtime", 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": "xai/grok-voice/realtime",
      "input": {
        "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
      },
      "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": "xai/grok-voice/realtime",
  "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": 1494,
    "usd": "1.494",
    "charged": 1494,
    "refunded": 0
  },
  "input": {
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  },
  "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
    },
    "text": "",
    "duration": 5
  },
  "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} | Jawapan lisan daripada ejen Grok, dihantar sebagai WAV mono pada 24 kHz. |
| `text` | string | Teks yang mengiringi pertuturan ejen: rentetan kosong menunjukkan bahawa Grok tidak menyediakan transkrip; jika tidak, teks tersebut mengandungi transkrip. |
| `duration` | number | Tempoh audio yang dijana, diukur dalam saat. |

## Related models

- [Grok Voice](https://doitong.com/developers/models/xai/grok-voice.md) (`xai/grok-voice`): $0.00083 / second of the voice session
- [MMAudio V2](https://doitong.com/developers/models/mmaudio-v2.md) (`mmaudio-v2`): $0.001 / second
- [DeepFilterNet 3](https://doitong.com/developers/models/deepfilternet3.md) (`deepfilternet3`): $0.001 / second of input audio
- [Demucs](https://doitong.com/developers/models/demucs.md) (`demucs`): $0.0007 / second of input audio
- [ElevenLabs Audio Isolation](https://doitong.com/developers/models/elevenlabs/audio-isolation.md) (`elevenlabs/audio-isolation`): $0.10 / minute of input file
- [Elevenlabs Sound Effects V2](https://doitong.com/developers/models/elevenlabs/sound-effects/v2.md) (`elevenlabs/sound-effects/v2`): $0.002 / second
- [ElevenLabs Voice Changer](https://doitong.com/developers/models/elevenlabs/voice-changer.md) (`elevenlabs/voice-changer`): $0.30 / minute of input audio
- [FFmpeg API \[Merge Audios\]](https://doitong.com/developers/models/ffmpeg-api/merge-audios.md) (`ffmpeg-api/merge-audios`): $0.00017 / second of processing time

## Links

- HTML page: https://doitong.com/developers/models/xai/grok-voice/realtime
- 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=xai/grok-voice/realtime
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/xai/grok-voice/realtime