xAI launches Grok Voice Transcribe 2.0, claiming 2x accuracy in calls and voice commands
SpaceXAI · x · 2026-09-19
xAI has released Grok Voice Transcribe 2.0, billed as the world's most accurate speech transcription model. The company says it is twice as accurate as its predecessor on customer-support calls, spoken credentials, and short voice commands.
A showcased deployment: Atlassian uses it in Loom, where it captures dictated user instructions more accurately — enabling a workflow of dictating change requests in Loom and exporting them straight to Cursor for AI coding.
Related event: xAI Launches Grok Voice Transcribe 2.0, Tops Streaming ASR Leaderboard(15 posts)→
More from Multimodal
- Seedance Draft on Plot Party: cheaper AI video prototyping before final renders — umesh_ai · 2026-11-04
- Sampler face-off at 8-16 steps on flow models: grids and LPIPS data — YakovSava · 2026-11-04
- INT8 isn't the problem: I benchmarked samplers on INT8 flow models — YakovSava · 2026-11-04
- Seedance 2.5 AI video of a wild Malfoy is turning heads — nikola_mr64990 · 2026-11-04
- Free course covers the 4 hard problems of production generative media agents — Al_Grigor · 2026-11-04
- PixelBench: testing multimodal models pixel-by-pixel instead of with QA — bdsqlsz · 2026-11-04