# Grok Voice · Realtime API

> Grok balss aģenta reāllaika variants straumētām, divvirzienu audio un teksta sarunām

Balss aģents tiešsaistes lietotnēm, piemēram, asistentiem un tālruņa aģentiem, kas veidots ap divvirzienu audio un teksta straumēšanu. Ievades atbilst standarta balss modelim: `audio_url` lietotāja runai, neobligātas personas instrukcijas `prompt`, balss izvēle `voice` un neobligāti `tools` piekļuvei tīmeklim, X vai MCP. Tas atgriež runātu WAV audio, tā ilgumu un atšifrējumu.

- 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/lv/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 |  |  | Lietotāja runas audio URL, ierobežots līdz 10 minūtēm un 50 MB. Var norādīt visbiežāk izmantotos audio formātus; pirms Grok saņem audio, tas tiek pārveidots par mono PCM ar 16 bitu paraugiem un 24 kHz. Aģents uz ierakstu atbild ar runu. |
| `prompt` |  | string \| null | no |  | ≤ 20000 characters | Neobligātas sistēmas instrukcijas, kas nodrošina sarunas kontekstu un Grok noklusējuma vietā nosaka personu; ja tās netiek norādītas, tiek saglabāta noklusējuma persona. |
| `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` | Izvēlieties iebūvētu xAI balsi, lai aizstātu Grok noklusējuma balsi aģenta atbildē; ja tā nav iestatīta, tiek saglabāta noklusējuma balss. |
| `tools` |  | object {mcp_servers, web_search, x_search} | no | `{"mcp_servers":[],"web_search":{"enabled":false},"x_search":{"enabled":false}}` |  | Aģenta rīku konfigurācija servera puses lietošanai; file_search/collections ir izslēgti no tipizētās konfigurācijas ZDR dēļ. Visi rīki sākotnēji ir atspējoti; atbalstītās opcijas ietver attālos MCP rīkus, tīmekļa rīkus un X rīkus. |
| `tools.mcp_servers` |  | array of object {allowed_tools, authorization, enabled, headers, server_description, server_label, server_url} | no |  |  | Attālie MCP serveri, ar kuriem modeļa nodrošinātājs izveido savienojumu rīku izpildei. |
| `tools.mcp_servers[].allowed_tools` |  | array of string \| null | no |  | ≥ 1 items | Neobligāts saraksts, kas norāda, kuri rīku nosaukumi tiek atklāti šajā serverī. |
| `tools.mcp_servers[].authorization` |  | string \| null | no |  |  | Sensitīva autorizācijas vērtība, kas tiek nosūtīta tikai modeļa nodrošinātājam. |
| `tools.mcp_servers[].enabled` |  | boolean | no | `true` |  | Servera iekļaušanas karodziņš; false izslēdz serveri. |
| `tools.mcp_servers[].headers` |  | object \| null | no |  |  | Sensitīvi MCP pieprasījumu galveņu dati, kas tiek nosūtīti tikai modeļa nodrošinātājam. |
| `tools.mcp_servers[].server_description` |  | string \| null | no |  | ≤ 2000 characters | Apraksts, kurā izklāstītas šī servera nodrošinātās iespējas. |
| `tools.mcp_servers[].server_label` |  | string | yes |  | 1 – 128 characters | Servera etiķete, ko modeļa nodrošinātājs izmanto savu rīku identificēšanai un to nosaukumu prefiksēšanai. |
| `tools.mcp_servers[].server_url` |  | string | yes |  | ≥ 1 characters | Izsaucēja nodrošināta HTTP(S) adrese MCP serverim, ar kuru Grok attālināti izveido savienojumu, izmantojot Streaming HTTP/SSE transportus. |
| `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}` |  | Nodrošinātāja pārvaldīta tīmekļa meklēšana, kas ir atspējota, ja vien enabled nav true. |
| `tools.web_search.allowed_domains` |  | array of string \| null | no |  | 1 – 5 items | Meklēšanas rezultātu domēnu ierobežojums: norādiet līdz pieciem domēniem, izlaižot protokolus un ceļus. |
| `tools.web_search.enable_image_understanding` |  | boolean \| null | no |  |  | Atļauja aģentam pārbaudīt tīmekļa meklējumos atrastos attēlus. |
| `tools.web_search.enabled` |  | boolean | no | `false` |  | Aģenta piekļuve tīmekļa meklēšanai: true pievieno web_search vietnei session.tools un atļauj tīmekļa meklēšanu; noklusējums to atstāj atspējotu. |
| `tools.web_search.excluded_domains` |  | array of string \| null | no |  | 1 – 5 items | No meklēšanas rezultātiem izslēdzamie domēni, ne vairāk kā pieci ieraksti, izlaižot protokolus un ceļus. |
| `tools.web_search.location` |  | object {city, country, region, timezone} \| null | no |  |  | Neobligāta atrašanās vieta meklēšanas rezultātu ģeogrāfiskai pielāgošanai. |
| `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}` |  | Nodrošinātāja pārvaldīta X meklēšana, kas ir atspējota, ja vien enabled nav true. |
| `tools.x_search.allowed_x_handles` |  | array of string \| null | no |  | 1 – 20 items | X rokturi, kuru ziņas var parādīties rezultātos; ne vairāk kā 20 rokturi. |
| `tools.x_search.enable_image_understanding` |  | boolean \| null | no |  |  | Atļauja aģentam pārbaudīt X atrastos attēlus. |
| `tools.x_search.enable_video_understanding` |  | boolean \| null | no |  |  | Atļauja aģentam pārbaudīt X atrastos video. |
| `tools.x_search.enabled` |  | boolean | no | `false` |  | Piekļuve X ziņām, izmantojot meklēšanu: true pievieno x_search vietnei session.tools, lai aģents varētu meklēt šīs ziņas; noklusējums to atstāj atspējotu. |
| `tools.x_search.excluded_x_handles` |  | array of string \| null | no |  | 1 – 20 items | X rokturi, kuru ziņas tiek izslēgtas; ne vairāk kā 20 rokturi. |
| `tools.x_search.from_date` |  | string \| null | no |  |  | Agrākais ziņu datums ISO formātā YYYY-MM-DD. |
| `tools.x_search.to_date` |  | string \| null | no |  |  | Vēlākais ziņu datums ISO formātā YYYY-MM-DD. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Pārbaudi var atslābināt, iestatot false, ja izsaucējam ir atļauja. |

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} | Grok aģenta izrunātā atbilde, kas tiek nodrošināta kā mono WAV ar 24 kHz. |
| `text` | string | Teksts, kas pavada aģenta runu: tukša virkne norāda, ka Grok nav nodrošinājis transkripciju; pretējā gadījumā tajā ir transkripcija. |
| `duration` | number | Ģenerētā audio garums sekundēs. |

## 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