Grok Voice Transcribe 2.0 Tops Streaming ASR Benchmark With 2.7% WER
XFreeze · x · 2026-09-19
Per third-party reports, xAI released Grok Voice Transcribe 2.0, ranking #1 on Artificial Analysis' streaming ASR benchmark for both final and first-partial transcript accuracy. Word error rate dropped to 2.7% from 3.9% on v1.0 — roughly 31% fewer errors — beating Meta Muse Voice Transcribe, Cartesia Ink, ElevenLabs Scribe Realtime and every other streaming ASR model tested.
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