x-ai: Grok STT

xAI's Grok speech-to-text model. Transcribes audio files into text across 25 languages with word-level timestamps, multichannel transcription, speaker diarization, and key-term biasing.

cloudflareWorkersAI/xai/grok-stt

xAI's Grok speech-to-text model. Transcribes audio files into text across 25 languages with word-level timestamps, multichannel transcription, speaker diarization, and key-term biasing.

Specifications & capabilities

Input
audio
Output
transcription
Capabilities
audioInput

Published prices

1–2 / 2

xai/grok-stt ↗

$0.0017

Inference provider
cloudflareWorkersAI
Platform
xAI
Unit
audio_minute
Currency
USD
Billing conditions
Billing label
Per audio minute
Pricing via
Cloudflare AI Gateway

xai/grok-stt ↗

$0.0033

Inference provider
cloudflareWorkersAI
Platform
xAI
Unit
catalog_quote
Currency
USD
Billing conditions
label
input_audio_minutes_streaming
Billing label
input_audio_minutes_streaming
Pricing via
Cloudflare AI Gateway

Provider specifications & access

1–1 / 1

Grok STT ↗

source model id
xai/grok-stt
hosting
third-party
platforms
  • xAI
architecture
input_modalities
  • audio
output_modalities
  • transcription
capabilities

    Safety assessments

    1–1 / 1

    Foundation Model Transparency Index 2025 ↗

    14 / 100

    source id
    stanfordFMTI
    canonical model id
    cloudflareWorkersAI/xai/grok-stt
    taxonomy
    transparency
    hazard category
    transparency
    hazard name
    Organization transparency
    policy area
    xAI
    assessment type
    organization-level disclosure
    metric
    disclosure_score
    result label
    14 / 100
    sample size
    100
    updated at
    2026-11-09T18:08:05.227Z

    Original sources

    1–3 / 3

    GitHub · Source snapshot ↗

    Cloudflare AI · Catalog ↗

    GitHub · Catalog ↗

    Source links

    1–2 / 2

    Explore more models

    Models

    Loading
    EVIDENCE / COMPARISON

    Benchmarks

    Explore every benchmark

    Loading

    These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

    Install TensorTrace