Grok Speech by @xai

Text-to-Speech: 5 voices, 20 languages, expressive tags like [laugh] and <whisper>

Speech-to-Text: 25 languages, word-level timestamps, speaker diarization

Try it here 👇 pic.twitter.com/T646xffeGq

— Replicate (@replicate) 29 avril 2026

Grok Speech by @xai Text-to-Speech: 5 voices, 20 languages, expressive tags like [laugh] and Speech-to-Text: 25 languages, word-level timestamps, speaker diarization Try it here

→ View original post on X — @replicate