Evidence and sources
Released 18 Apr 2026Maker HQ: US (according to xAI's own website)
All rankings:
#710 on OpenRouter this week
#772 on OpenRouter this monthSources: Models.dev data, llminfo researchPrimary data from Models.dev
from llminfo research: release date
Advantages and trade-offs
Compared with 10 representative transcription models
Advantages
Trade-offs
No open weights
The weights aren't public, so you can't run it yourself.
Input & output
as stated by the model's providersAudio
Video
Text
Also known as: grok-speech-to-text, spacexai/grok-stt, xai speech to text v1, xai-speech-to-text-v1, xai/grok-speech-to-text, xai/speech-to-text/v1
Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works