xai/grok-stt/speech-to-textFrom 0.01 credits per secondxAI's Grok speech-to-text, generally available since April 2026: send an audio URL and get the transcript back as text. 25 languages with automatic detection, separate transcripts per channel, key-term hints and numbers in written form.
Call it with the model name xai/grok-stt/speech-to-text on POST /jobs/createTask, from 0.01 credits per second ($0.0001). New accounts get 30 free credits to try it in the Playground first.
- Speech to Text
- 25 languages
Your Grok STT · Speech to Text runs
Tasks from your account on this model, from the website, the Playground and the API.