Speech-to-text model with word-level timestamps, speaker diarization, multichannel audio, and streaming
Specification
most-agreed values
Context
15K
Max output
15K
Released
2026-09-17
Knowledge cutoff
—
Retires
—
Open weights
no
Input
audio
Output
text
Available from 1 host
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| zenmux · x-ai | — | — | — | — | 15K | 15K | — |
More from xAI
most-hosted first