# Grok Voice · Realtime API

> Toleo la wakati halisi la wakala wa sauti wa Grok kwa utiririshaji na mazungumzo ya sauti na maandishi ya pande mbili

Wakala wa sauti anayelengwa kwa programu za moja kwa moja kama wasaidizi na mawakala wa simu, aliyejengwa kuzunguka utiririshaji wa sauti na maandishi katika pande zote mbili. Maingizo yanafanana na modeli ya kawaida ya sauti: `audio_url` kwa hotuba ya mtumiaji, maelekezo ya persona ya `prompt` ya hiari, chaguo la `voice` na `tools` za hiari za ufikiaji wa wavuti, X au MCP. Hurejesha sauti ya WAV ya hotuba, muda wake na manukuu.

- 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/sw/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 ya sauti ya usemi wa mtumiaji, yenye ukomo wa dakika 10 na 50 MB. Miundo ya sauti inayotumika sana inaweza kutolewa; kabla Grok haijapokea sauti, hubadilishwa kuwa mono PCM yenye sampuli za biti 16 katika 24 kHz. Wakala hujibu rekodi hiyo kwa usemi. |
| `prompt` |  | string \| null | no |  | ≤ 20000 characters | Maelekezo ya hiari ya mfumo yanayotoa muktadha wa mazungumzo na kubainisha persona badala ya chaguomsingi ya Grok; kuyaacha huhifadhi persona hiyo chaguomsingi. |
| `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` | Chagua sauti iliyojengewa ndani ya xAI ili kubatilisha chaguomsingi ya Grok kwa jibu la wakala; kuacha hii bila kuwekwa huhifadhi sauti hiyo chaguomsingi. |
| `tools` |  | object {mcp_servers, web_search, x_search} | no | `{"mcp_servers":[],"web_search":{"enabled":false},"x_search":{"enabled":false}}` |  | Usanidi wa zana za wakala kwa matumizi ya upande wa seva, ukiondoa file_search/collections kwenye usanidi wenye aina kwa sababu ya ZDR. Zana zote huanza zikiwa zimezimwa; chaguo zinazotumika ni pamoja na zana za MCP za mbali, zana za wavuti na zana za X. |
| `tools.mcp_servers` |  | array of object {allowed_tools, authorization, enabled, headers, server_description, server_label, server_url} | no |  |  | Seva za MCP za mbali ambazo mtoa modeli huunganisha nazo kwa utekelezaji wa zana. |
| `tools.mcp_servers[].allowed_tools` |  | array of string \| null | no |  | ≥ 1 items | Orodha ya hiari inayobainisha majina ya zana ambazo seva hii hutoa. |
| `tools.mcp_servers[].authorization` |  | string \| null | no |  |  | Thamani nyeti ya uidhinishaji inayotumwa pekee kwa mtoa modeli. |
| `tools.mcp_servers[].enabled` |  | boolean | no | `true` |  | Alama ya kujumuisha seva; false huiondoa seva. |
| `tools.mcp_servers[].headers` |  | object \| null | no |  |  | Vichwa nyeti vya maombi ya MCP, vinavyotumwa pekee kwa mtoa modeli. |
| `tools.mcp_servers[].server_description` |  | string \| null | no |  | ≤ 2000 characters | Maelezo yanayoonyesha uwezo ambao seva hii hutoa. |
| `tools.mcp_servers[].server_label` |  | string | yes |  | 1 – 128 characters | Lebo ya seva inayotumiwa na mtoa modeli kutambua zana zake na kuweka kiambishi kwenye majina yake. |
| `tools.mcp_servers[].server_url` |  | string | yes |  | ≥ 1 characters | Anwani ya HTTP(S) iliyotolewa na mpigaji kwa seva ya MCP ambayo Grok huunganisha nayo kwa mbali kupitia usafirishaji wa 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}` |  | Utafutaji wa wavuti unaosimamiwa na mtoa huduma, umezimwa isipokuwa enabled iwe true. |
| `tools.web_search.allowed_domains` |  | array of string \| null | no |  | 1 – 5 items | Kizuizi cha kikoa kwa matokeo ya utafutaji: bainisha hadi vikoa vitano, ukiondoa itifaki na njia. |
| `tools.web_search.enable_image_understanding` |  | boolean \| null | no |  |  | Ruhusa kwa wakala kuchunguza picha zilizopatikana kupitia utafutaji wa wavuti. |
| `tools.web_search.enabled` |  | boolean | no | `false` |  | Ufikiaji wa utafutaji wa wavuti kwa wakala: true huongeza web_search kwenye session.tools na kuruhusu utafutaji wa wavuti; chaguomsingi huiacha ikiwa imezimwa. |
| `tools.web_search.excluded_domains` |  | array of string \| null | no |  | 1 – 5 items | Vikoa vya kuondoa kwenye matokeo ya utafutaji, vikiwa na ukomo wa maingizo matano na itifaki na njia zimeondolewa. |
| `tools.web_search.location` |  | object {city, country, region, timezone} \| null | no |  |  | Eneo la hiari la kurekebisha matokeo ya utafutaji kijiografia. |
| `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}` |  | Utafutaji wa X unaosimamiwa na mtoa huduma, umezimwa isipokuwa enabled iwe true. |
| `tools.x_search.allowed_x_handles` |  | array of string \| null | no |  | 1 – 20 items | Hushughulikia X ambazo machapisho yake yanaweza kuonekana kwenye matokeo, zikiwa na ukomo wa hushughulikia 20. |
| `tools.x_search.enable_image_understanding` |  | boolean \| null | no |  |  | Ruhusa kwa wakala kuchunguza picha zilizopatikana kwenye X. |
| `tools.x_search.enable_video_understanding` |  | boolean \| null | no |  |  | Ruhusa kwa wakala kuchunguza video zilizopatikana kwenye X. |
| `tools.x_search.enabled` |  | boolean | no | `false` |  | Ufikiaji wa machapisho ya X kupitia utafutaji: true huongeza x_search kwenye session.tools ili wakala aweze kutafuta machapisho hayo; chaguomsingi huiacha ikiwa imezimwa. |
| `tools.x_search.excluded_x_handles` |  | array of string \| null | no |  | 1 – 20 items | Hushughulikia X ambazo machapisho yake yameondolewa, zikiwa na ukomo wa hushughulikia 20. |
| `tools.x_search.from_date` |  | string \| null | no |  |  | Tarehe ya mapema zaidi ya machapisho, iliyoonyeshwa katika umbizo la ISO YYYY-MM-DD. |
| `tools.x_search.to_date` |  | string \| null | no |  |  | Tarehe ya hivi karibuni zaidi ya machapisho, iliyoonyeshwa katika umbizo la ISO YYYY-MM-DD. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Ukaguzi unaweza kulegezwa kwa kuweka false, ikiwa mpigaji simu ameidhinishwa. |

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} | Jibu la sauti kutoka kwa wakala wa Grok, linalowasilishwa kama WAV ya mono katika 24 kHz. |
| `text` | string | Maandishi yanayoandamana na matamshi ya wakala: mfuatano tupu unaonyesha kuwa Grok hakutoa unukuzi; vinginevyo, una unukuzi. |
| `duration` | number | Urefu wa sauti inayozalishwa, unaopimwa kwa sekunde. |

## 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