Grok Voice Transcribe 2.0
Speech-to-text model with word-level timestamps, speaker diarization, multichannel audio, and streaming
BENCHMARKS
Not in the Epoch Capabilities Index. Epoch benchmarks what it can run, so this is a gap in coverage, not a poor result.
xAI's past year
19 release days in the past year, about one every 19 days. The next is expected around Nov 10, 2026. Forecasts ↗
NovDecJanFebMarAprMayJunJulAugSepOctNov
Specifications
RELEASE DATESep 17, 2026
WEIGHTSClosed weights
CONTEXT WINDOWNot listed
MAX OUTPUT0
REASONINGNot listed
TOOL CALLINGNot listed
INPUTSaudio/wav, audio/mpeg, audio/ogg, audio/flac, audio/aac, audio/mp4
OUTPUTStext
Specifications and prices from Models.dev; availability and limits may differ by provider. Benchmarks from Epoch AI (CC BY 4.0), LiveBench and the other sources named above.