x.ai grok Update Version Grok Voice Transcribe 2.0

Sep 18, 2026 release of Grok Voice Transcribe 2.0, a speech-to-text model with improved accuracy, multilingual support, and advanced transcription controls. It will soon become the default in the Speech-to-Text API, while Grok Voice Transcribe 1.0 will be deprecated.

• Improved speech-to-text accuracy, including better performance on noisy, multilingual, and real-world audio.
• Automatic language detection with support for dozens of languages and mid-recording language switching.
• Batch and streaming transcription for recorded files, URLs, and real-time audio streams.
• Word-level timestamps with confidence scores.
• Speaker diarization at no additional cost.
• Multichannel transcription for up to 8 channels.
• Key term biasing for up to 100 domain terms per request.
• Text formatting for numbers, dates, currencies, phone numbers, and email addresses.
• Filler word removal.
• Smart turn detection for voice agents.

• Existing Speech-to-Text API integrations get the accuracy improvement with no code changes.
• Pricing is unchanged from Grok Voice Transcribe 1.0: batch transcription is $0.10 per hour and streaming is $0.20 per hour.
• To remain on the previous model during the transition, pin grok-voice-transcribe-1.0.
• Grok Voice Transcribe 1.0 will be deprecated in the coming weeks.
• Grok Voice Transcribe 2.0 will soon be the default in the Speech-to-Text API.

• Release announcement
  https://x.ai/blog/grok-voice-transcribe-2-0

Product Information

Vendor: x.ai

Product: grok

Product type: Other

Platform: Web

Version: Grok Voice Transcribe 2.0

Vendor information published: Sep 18, 2026

Original release notes: View on vendor site

Published on updatealert.io: Sep 18, 2026

Description: AI assistant for conversation, analysis, and content generation.