# Grok Voice · Realtime API

> Varian realtime agen suara Grok untuk streaming dan percakapan audio serta teks dua arah

Agen suara untuk aplikasi langsung seperti asisten dan agen telepon, dengan streaming audio dan teks dua arah. Inputnya sama dengan model suara standar: `audio_url` untuk ucapan pengguna, instruksi persona `prompt` opsional, pilihan `voice`, dan `tools` opsional untuk akses web, X, atau MCP. Mengembalikan audio WAV ucapan, durasi, 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.ru/v1/run/xai/grok-voice/realtime`
- Quote: `POST https://api.doitong.ru/v1/quote/xai/grok-voice/realtime`
- Docs page: https://doitong.com/id/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.ru/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 ucapan pengguna, dibatasi hingga 10 menit dan 50 MB. Sebagian besar format audio umum dapat diberikan; sebelum Grok menerima audio, audio dikonversi menjadi mono PCM dengan sampel 16-bit pada 24 kHz. Agen merespons rekaman tersebut dengan ucapan. |
| `prompt` |  | string \| null | no |  | ≤ 20000 characters | Instruksi sistem opsional yang menyediakan konteks percakapan dan menentukan persona sebagai pengganti bawaan Grok; jika dihilangkan, persona bawaan tetap digunakan. |
| `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 bawaan untuk menggantikan suara bawaan Grok pada balasan agen; jika tidak diatur, suara bawaan tersebut tetap digunakan. |
| `tools` |  | object {mcp_servers, web_search, x_search} | no | `{"mcp_servers":[],"web_search":{"enabled":false},"x_search":{"enabled":false}}` |  | Konfigurasi alat agen untuk penggunaan sisi server, tidak menyertakan file_search/collections dari konfigurasi bertipe karena ZDR. Semua alat dinonaktifkan pada awalnya; opsi yang didukung mencakup alat MCP jarak jauh, alat web, dan alat X. |
| `tools.mcp_servers` |  | array of object {allowed_tools, authorization, enabled, headers, server_description, server_label, server_url} | no |  |  | Server MCP jarak jauh yang terhubung oleh penyedia model untuk eksekusi alat. |
| `tools.mcp_servers[].allowed_tools` |  | array of string \| null | no |  | ≥ 1 items | Daftar opsional yang menentukan nama alat yang diekspos server ini. |
| `tools.mcp_servers[].authorization` |  | string \| null | no |  |  | Nilai otorisasi sensitif yang dikirim hanya kepada penyedia model. |
| `tools.mcp_servers[].enabled` |  | boolean | no | `true` |  | Flag penyertaan server; false mengecualikan server. |
| `tools.mcp_servers[].headers` |  | object \| null | no |  |  | Header sensitif untuk permintaan MCP, dikirim hanya kepada penyedia model. |
| `tools.mcp_servers[].server_description` |  | string \| null | no |  | ≤ 2000 characters | Deskripsi yang menguraikan kemampuan yang disediakan server ini. |
| `tools.mcp_servers[].server_label` |  | string | yes |  | 1 – 128 characters | Label server yang digunakan penyedia model untuk mengidentifikasi alatnya dan memberi awalan pada namanya. |
| `tools.mcp_servers[].server_url` |  | string | yes |  | ≥ 1 characters | Alamat HTTP(S) yang diberikan pemanggil untuk server MCP yang terhubung Grok dari jarak jauh melalui transport 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}` |  | Pencarian web yang dikelola penyedia, dinonaktifkan kecuali enabled bernilai true. |
| `tools.web_search.allowed_domains` |  | array of string \| null | no |  | 1 – 5 items | Pembatasan domain untuk hasil pencarian: tentukan maksimal lima domain, tanpa protokol dan path. |
| `tools.web_search.enable_image_understanding` |  | boolean \| null | no |  |  | Izin bagi agen untuk memeriksa gambar yang ditemukan melalui pencarian web. |
| `tools.web_search.enabled` |  | boolean | no | `false` |  | Akses pencarian web untuk agen: true menambahkan web_search ke session.tools dan mengizinkan pencarian web; bawaan membiarkannya dinonaktifkan. |
| `tools.web_search.excluded_domains` |  | array of string \| null | no |  | 1 – 5 items | Domain yang dikecualikan dari hasil pencarian, dibatasi hingga lima entri tanpa protokol dan path. |
| `tools.web_search.location` |  | object {city, country, region, timezone} \| null | no |  |  | Lokasi opsional untuk menyesuaikan hasil pencarian secara geografis. |
| `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}` |  | Pencarian X yang dikelola penyedia, dinonaktifkan kecuali enabled bernilai true. |
| `tools.x_search.allowed_x_handles` |  | array of string \| null | no |  | 1 – 20 items | Handle X yang postingannya dapat muncul dalam hasil, dibatasi hingga 20 handle. |
| `tools.x_search.enable_image_understanding` |  | boolean \| null | no |  |  | Izin bagi agen untuk memeriksa gambar yang ditemukan di X. |
| `tools.x_search.enable_video_understanding` |  | boolean \| null | no |  |  | Izin bagi agen untuk memeriksa video yang ditemukan di X. |
| `tools.x_search.enabled` |  | boolean | no | `false` |  | Akses ke postingan X melalui pencarian: true menambahkan x_search ke session.tools agar agen dapat mencari postingan tersebut; bawaan membiarkannya dinonaktifkan. |
| `tools.x_search.excluded_x_handles` |  | array of string \| null | no |  | 1 – 20 items | Handle X yang postingannya dikecualikan, dibatasi hingga 20 handle. |
| `tools.x_search.from_date` |  | string \| null | no |  |  | Tanggal paling awal untuk postingan, dinyatakan dalam format ISO YYYY-MM-DD. |
| `tools.x_search.to_date` |  | string \| null | no |  |  | Tanggal paling akhir untuk postingan, dinyatakan dalam format ISO YYYY-MM-DD. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Penyaringan dapat dilonggarkan dengan menetapkan false, jika pemanggil berwenang. |

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.ru/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.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/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.ru/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.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": "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.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} | Balasan lisan dari agen Grok, dikirim sebagai WAV mono pada 24 kHz. |
| `text` | string | Teks yang menyertai ucapan agen: string kosong menunjukkan bahwa Grok tidak menyediakan transkrip; jika tidak, teks tersebut berisi transkrip. |
| `duration` | number | Panjang audio yang dibuat, diukur dalam detik. |

## 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.ru/v1/models/xai/grok-voice/realtime