All tasks / Models

Grok Voice Transcribe 2.0

xAI's speech-to-text model behind its STT API, with batch and streaming modes in 38+ languages.

  • xAI
  • Closed
  • Released 18 Sep 2026

Official page

Where it ranks

  • S
    Transcription
    Models · Cloud · 2.3% on Artificial Analysis Speech to Text: AA-WER v2 (non-streaming)

Facts

Vendor
xAI
Family
Grok Voice Transcribe
Released
18 Sep 2026
Weights
Closed: API and apps only
License
proprietary
API price
$0.0017 per minute of audio (Batch $0.10 per hour of audio divided by 60; streaming is $0.20 per hour.)
Last verified
18 Oct 2026

Price from docs.x.ai, 18 Oct 2026.

Benchmark results

BenchmarkResultEntry on the leaderboardAs ofSource
Artificial Analysis Speech to Text: AA-WER Streaming2.7%Grok Voice Transcribe 2.0 (Streaming)
AA-WER Streaming index (final transcripts), provider SpaceXAI; embedded value 0.027279 converted to percent and rounded; page shows no last-updated date.
19 Oct 2026artificialanalysis.ai
Artificial Analysis Speech to Text: AA-WER v2 (non-streaming)2.3%Grok Voice Transcribe 2.0
AA-WER v2 (non-streaming), provider SpaceXAI; embedded value 0.0229 converted to percent and rounded; page shows no last-updated date.
18 Oct 2026artificialanalysis.ai

Where you can use it

No tracked tool lists this model yet.

Compare

Alternatives to Grok Voice Transcribe 2.0

Sources