Grok Speech to Text
Model Information
Grok Speech to Text (STT) is xAI's standalone speech recognition API for batch and real-time transcription. It supports multilingual transcription, word-level timestamps, speaker diarization, multichannel audio, keyterm prompting, Inverse Text Normalization, and real-time interim results over WebSocket.
Model ID
xai.grok-stt
Use this ID when making API calls to reference this model
Provider
SpaceXAI
Model Type
ASR
Accuracy Tier
premium
Release Date
April 17, 2026
Supported Languages
arcsdanlenfilfrdehiiditjakomkmsfaplptroruessvthtrvi
Automatic Language Detection: Yes
Streaming Transcription Languages
arcsdanlenfilfrdehiiditjakomkmsfaplptroruessvthtrvi
Performance & Cost
Cost
$0.10000/hour
$0.00003/second
Maximum File Size
500.00 MB
Features
Supported capabilities and functionalities
Core Features
Punctuation
Diarization
Streaming
Speaker Labels
Word Timestamps
Confidence Scores
Custom Vocabulary
Profanity Filtering
Noise Reduction
Voice Activity Detection
Subtitle Formats
SRT Support
VTT Support
Technical Specifications
Input/output formats and technical details
Subtitle Format Support
No subtitle formats supported
Supported Audio Encodings
WAVMP3OGGOpusFLACAACMP4M4AMKVPCMmulawalaw
Supported Sample Rates
8000 Hz16000 Hz22050 Hz24000 Hz44100 Hz48000 Hz