Grok STT 1.0

xAI's speech-to-text model. Transcribes audio files into text with word-level timestamps, speaker diarization, multichannel transcription, and inverse text normalization across 25 languages via the /v1/audio/transcriptions endpoint.

grok-stt-1-0
STABLEGet StartedView uptime
0 context
Starting at $0.00/M input tokens
Starting at $0.00/M output tokens

Select Provider

All Providers for Grok STT 1.0

LLM Gateway routes requests to the best providers that are able to handle your prompt size and parameters.

xAI
Context:
Input
$0
/M tokens
Cached
/M tokens
Output
$0
/M tokens
Get Started