Grok Voice Transcribe 2.0 cuts short-phrase WER from 20.6% to 6.8%, tops streaming STT
nima_owji · x · 2026-09-20
Grok Voice Transcribe 2.0 is out, and the author argues it's a real jump rather than a rename:
- 2x accuracy improvement over version 1.0
- Ranks #1 in streaming STT on Artificial Analysis
- Word error rate on short phrases dropped from 20.6% to 6.8%
- Pricing unchanged at $0.10 / $0.20
For developers building real-time transcription, captioning, or voice-input features, the streaming accuracy gains are the headline.
More from Models
- Bespoke Labs open-sources Nimble, an open Jev rival for fast typed decisions — RexDouglass · 2026-09-20
- LFM2.5-230M hits 192 tok/s on a phone CPU in llama.cpp test — Tall_Abrocoma_3533 · 2026-09-20
- Researchers Pan Apple Foundation Models CLI Chat as 'Embarrassing' — StefanoGogioso · 2026-09-20
- ChatGPT-6 Astra Cracks 108-Year-Old Unsolved WWI German Code — Andune88 · 2026-09-20
- Using Jev, the 'System One' classifier, to speed up self-hosted agent memory — FUNdationOne · 2026-09-20
- TypeSafe's Jev explained: typed answers in 70–500ms at $0.042 per 1M tokens — Sea_Supermarket_5891 · 2026-09-20