# grok-voice-transcribe-1.0 end of life

By Steven Van · 2026-10-01

xAI routes all grok-voice-transcribe-1.0 requests to the 2.0 model at the same price, which it says is more accurate, so existing API calls keep working.

Anyone still sending requests to [Grok](<https://creatorstoolbox.com/tools/grok>)'s grok-voice-transcribe-1.0 speech-to-text model has until October 2, 2026, when the model reaches end of life. xAI has [deprecated it](<https://docs.x.ai/developers/model-capabilities/audio/speech-to-text>), and all requests to that slug are routed to grok-voice-transcribe-2.0.

The price stays the same, and xAI says the newer model has higher accuracy. The 2.0 model is already the default when model is omitted, on both the REST endpoint and the WebSocket streaming endpoint. Code that names 1.0 explicitly will keep working through the routing, and setting model=grok-voice-transcribe-2.0 makes the switch explicit.

![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-1.0 end of life on Creators Toolbox](<https://creatorstoolbox.com/blog/grok-grok-voice-transcribe-1-0-end-of-life>)

---
Canonical source: https://creatorstoolbox.com/blog/grok-grok-voice-transcribe-1-0-end-of-life