← All model drops
Live drop
Grok Voice Transcribe 2.0
xAIDropped Sep 18, 2026
Streaming and batch speech-to-text with half the error rate of v1.0 across noisy, multilingual and telephony audio.
About this release
Live drop
xAIDropped Sep 18, 2026
Streaming and batch speech-to-text with half the error rate of v1.0 across noisy, multilingual and telephony audio.
About this release
Grok Voice Transcribe 2.0 is xAI’s latest speech-to-text model, built on the same audio foundation as Grok Voice. It supports batch and real-time streaming transcription with automatic language detection, mid-recording language switching, speaker diarization, word-level timestamps and key-term biasing. It ranks first on the Artificial Analysis streaming accuracy leaderboard and is available via the Speech-to-Text API at unchanged pricing.
Read the official xAI launch pageFirst builds incoming — this lane fills in automatically as people start building with Grok Voice Transcribe 2.0. Know one? Submit the URL.