Choose Auto, TokenLab Verified, or Official for each request, with prices shown up front. See what's new

xAI: Grok Voice STT

Grok Voice STT converts recorded audio into text. Language hints and timestamp controls make it useful for transcripts that will feed captioning, search, or a later text-analysis step.
Compare models
grok-voice-stt
AvailablexAISpeech to TextSync
Price
From $0.000028
Modalities
Audio

About Grok Voice STT

Grok Voice STT is xAI's speech-to-text model, turning recorded audio into text transcripts. It accepts common audio file formats and returns word-level timestamps, and xAI separately documents streaming, speaker and channel separation, and number and currency formatting by language. Use it for captions, searchable meeting records, and call transcripts that feed later text analysis.

Where it works well

  • Word-level timestamps make it direct to build captions, jump-to-moment search, and subtitle files from the transcript.
  • xAI documents speaker diarization and multichannel transcription as native options; check the current model details before relying on them here.
  • Language hints and a prompt keyword steer recognition toward product names and jargon.
  • Text formatting renders numbers, dates, and currencies the way the spoken language writes them.

When to choose another model

  • It produces transcripts only; summarizing, translating, or answering from the audio needs a text model after it.
  • Very noisy recordings may need the voice-detection threshold tuned or cleaner input before accuracy is acceptable.

Getting started

  1. Create API key

    Create a key in Console, then use it with every model on the platform.

  2. Send your first request

    Copy the example for your language and run it against the endpoint.

    Speech to textTokenLab endpoint
    POST/v1/audio/transcriptions
    curl -X POST "https://api.tokenlab.sh/v1/audio/transcriptions" \
      -H "Authorization: Bearer sk-xxx" \
      -F file="@audio.mp3" \
      -F operation="stt" \
      -F response_format="json" \
      -F model="grok-voice-stt" \
      -F language="en"

Parameters

Speech to text

ParameterValues and limitsDefaultNotes
fileInputs: ≥ 1, ≤ 1Not providedSend one audio file in multipart/form-data. Maximum file size is 25 MiB.
languageNot providedNot providedThis field is accepted. The current public contract does not specify a complete value range or list. No additional values are promised. The omitted-field default is not verified.
promptNot providedNot providedNot provided
response_formatjson, text, verbose_jsonjsonNot provided
timestamp_granularitieswordNot providedNot provided

Pricing

The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.

Pricing

per second
Verified price
—
Official price
$0.000028per second

Usage & activity

Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.

Usage & availability

Last 24 hours
Requests
Success rate
P95 latency
Total tokens
Model performance
Metrics appear once privacy and data volume thresholds are met.

Data is based on aggregate user requests, excluding status checks.

Open in Console

Open Grok Voice STT in Console with a prompt ready to edit or send.

Help me try grok-voice-stt with a short audio request at /v1/audio/transcriptions. Show the result and cost.

Use cases

  • Meeting transcripts

    Transcribe a recorded call to text with word timings, then pass it to a summarizer for action items.

  • Subtitles for video

    Generate timed captions from an uploaded video's audio track using the word timings.

  • Call-center quality review

    Transcribe call recordings, then scan the text for compliance phrases. Speaker or channel labels are a native xAI option, not listed in the model details here.

Prompt examples

Transcribe this 20-minute podcast clip in English with word timestamps.

Transcribe the attached customer call, using the key terms 'Zyntra', 'OmniPlan', and 'SLA' to bias recognition.

Convert this Spanish voice memo to text and format the amounts as currency.

FAQ

What does Grok Voice STT do?

It converts audio into text. You send an audio file and it returns a transcript that can include word-level timestamps, depending on the options you set. xAI's native service also documents speaker labels and per-channel text.

Which audio formats can it read?

xAI lists twelve formats, including MP3, WAV, FLAC, and Opus. For the transcription endpoint linked here, upload an audio file no larger than 25 MB. xAI's native file endpoint documents a separate 500 MB ceiling that does not extend the upload limit here.

Does it support live transcription?

xAI documents a separate streaming endpoint with interim results. The model details linked here currently advertise file transcription only, so plan on uploading files. Check the current model contract before relying on live transcription.

How many languages does it cover?

xAI documents more than 25 languages for transcription and language-specific formatting. Pass a language hint when you know the language, so recognition does not have to guess.

Can it tell speakers apart?

xAI documents diarization and multichannel mode as separate native options. The model details linked here do not list diarize or multichannel, and asking for speaker labels in plain language does not enable them. Check the current model contract before relying on them.

How much does Grok Voice STT cost?

On TokenLab, Grok Voice STT costs $0.000028 per second. The pricing table above shows the full breakdown.

Which endpoint should Grok Voice STT use?

Use https://api.tokenlab.sh/v1/audio/transcriptions for Grok Voice STT. The request example below shows the matching code shape.

Which operations does Grok Voice STT support?

Grok Voice STT supports Speech to text. Select an operation above to see its endpoint and request example.

Compare Grok Voice STT

Sources

Reviewed Oct 2, 2026

More from Grok Voice

Related models