xAI: Grok Speech to Text

Name: Grok Speech to Text
Author: xAI

xai/grok-stt

active stt 1 provider

Playground

xAI's Grok speech-to-text: transcribes audio files in a single call or streams audio in real time over WebSocket with word-level timestamps, selected by endpoint (/v1/stt) rather than by a model parameter.

AuthorxAI

Languagesmultilingual

Statusactive

Quick start

Grok Speech to Text

Create an API key

Create API key

Make a request

Pick an SDK, request mode, and language. The model and provider route are already filled in.

ElevenLabs SDK streaming STT

Streams microphone or file audio through the ElevenLabs-compatible allmodels route.

import { ElevenLabsClient } from "elevenlabs";

const client = new ElevenLabsClient({
  apiKey: process.env.ALLMODELS_API_KEY,
  baseUrl: "https://api.allmodels.io/el"
});

const connection = await client.speechToText.realtime.connect({
  modelId: "xai/grok-stt",
  languageCode: "en"
}, {
  queryParams: {
    provider: {
      "only": [
        "grok"
      ]
    }
  }
});

// Send audio frames to connection, then handle transcript events.

Pass provider parameters

Pass provider preferences through the compatible SDK request options when you want to pin a route to a provider.

{
  queryParams: {
    provider: {
      only: ["grok"]
    }
  }
}

Providers

Different providers can host the same model. Choose one provider when you need a fixed backend, or let routing select among them.

ProviderSlugPer hourLatencyiModesUptime

xAI 11 params

grok

From $0.1

—

Synchronous · Streaming

xAI

11 documented provider parameters for this route.

Pricing

ModeLanguagePer hour

Rest Any $0.1

Streaming Any $0.2

Parameters

file formData · string · required

Audio file to transcribe. Max 500 MB. Must be the last field in the multipart form.

url formData · string · required

URL of an audio file to download and transcribe (server-side).

audio_format formData · string · optional

Format hint for raw/headerless audio.

3 enum values

Values

pcmmulawalaw

channels formData · integer · optional

Number of audio channels (2–8).

min 2max 8

diarize formData · boolean · optional

When true, enables speaker diarization.

default false

filler_words formData · boolean · optional

When true, filler words are included in the transcript.

default false

format formData · boolean · optional

When true, enables Inverse Text Normalization.

default false

keyterm formData · string · optional

A key term to bias transcription toward.

language formData · string · optional

Language code (e.g. en, fr, de). Used with format=true to enable text formatting.

multichannel formData · boolean · optional

When true, transcribes each audio channel independently.

default false

sample_rate formData · integer · optional

Sample rate in Hz. Only required for raw audio.

Supported languages

No reviewed language list for this model yet.

Features

Speech to text

Transcribes spoken audio to text.

speech_to_text

Streaming

Real-time streaming transcription over WebSocket (wss://api.x.ai/v1/stt).

streaming

Synchronous

Transcribes a fully-submitted audio file in a single synchronous request.

synchronous

Multilingual transcription

Supports 25 languages.

multilingual_transcription

Word-level timestamps

Returns a words array with text, start, and end.

word_timestamps

Code

ElevenLabs SDK streaming STT

Streams microphone or file audio through the ElevenLabs-compatible allmodels route.

import { ElevenLabsClient } from "elevenlabs";

const client = new ElevenLabsClient({
  apiKey: process.env.ALLMODELS_API_KEY,
  baseUrl: "https://api.allmodels.io/el"
});

const connection = await client.speechToText.realtime.connect({
  modelId: "xai/grok-stt",
  languageCode: "en"
}, {
  queryParams: {
    provider: {
      "only": [
        "grok"
      ]
    }
  }
});

// Send audio frames to connection, then handle transcript events.