Overview
SpaceXAI’s transcription model for batch and real-time speech recognition, improving multilingual accuracy, diarization, timestamps, and noisy real-world audio.
Grok Voice Transcribe 2.0
SpaceXAI’s transcription model for batch and real-time speech recognition, improving multilingual accuracy, diarization, timestamps, and noisy real-world audio.
Grok Voice Transcribe 2.0 is available in the Speech-to-Text API and is now the default model; 1.0 remains available but will be deprecated in the coming weeks.
MODEL NUMBER121
- First public date
- 2026-09-17
- Organization
- SpaceXAI
- Family
- Grok
01
Specifications
Only published specifications are shown.
- Input modalities
- Audio
- Output modalities
- Text
- Open weights
- No
- Status
- Current
02
Overview
Why it mattered
It turns the audio foundation behind Grok Voice into a dedicated transcription API and replaces the first-generation model without requiring integration changes.
PreviousGrok Voice Transcribe 1.0— · — ctx
CurrentGrok Voice Transcribe 2.0— · — ctx
04
Architecture & capabilities
Model capabilities
Audio transcriptionReal-time audioSpeaker diarizationSpeech endpointingMultilingual
05
Release history
SpaceXAI made Grok Voice Transcribe 2.0 available in the Speech-to-Text API on September 17 and announced it would become the default transcription model; Grok Voice Transcribe 1.0 entered a deprecation transition. The launch article is dated September 18.
View source06
Related models
Select a card to view the related model.
07
Sources
Suggest a correction
Copy this template, add the field, proposed value, and primary source, and share it with the archive maintainer.