# Grok Voice Transcribe 2.0

By Steven Van · 2026-09-01

A new transcription model joins Grok's Speech to Text API, but developers must opt in since 1.0 stays the default.

**grok-voice-transcribe-2.0** is now available in the [Grok](<https://creatorstoolbox.com/tools/grok>) Speech to Text API, alongside the original grok-voice-transcribe-1.0 model. The API accepts batch file uploads or real-time WebSocket streaming, supports 12 audio formats, word-level timestamps, multichannel transcription, and text formatting. The default model remains grok-voice-transcribe-1.0; developers who want the new model must set model=grok-voice-transcribe-2.0 explicitly. Details are in the [Speech to Text docs](<https://docs.x.ai/developers/model-capabilities/audio/speech-to-text>).

![Grok](<https://www.google.com/s2/favicons?domain=grok.com&sz=128>)

Grok

AI assistant by xAI — chat, reason, generate images, and analyze data with real-time information access.

[View Grok →](<https://creatorstoolbox.com/tools/grok>)

[Original source](<https://docs.x.ai/developers/model-capabilities/audio/speech-to-text>)

[Read Grok Voice Transcribe 2.0 on Creators Toolbox](<https://creatorstoolbox.com/blog/grok-grok-voice-transcribe-2-0>)

---
Canonical source: https://creatorstoolbox.com/blog/grok-grok-voice-transcribe-2-0