Grok Voice Transcribe 2.0 Tops AA-WER Streaming With 2.7% WER, Edging Out ElevenLabs and Cartesia
ArtificialAnlys · x · 2026-09-19
xAI has released Grok Voice Transcribe 2.0, its new speech-to-text model, which takes the #1 spot among 33 models on Artificial Analysis's AA-WER Streaming leaderboard with 2.7% WER and a 0.49s final transcript delay after end of speech.
It marks a clear jump from v1 (3.9% WER) and leads both Final Transcript and First Partial Transcript accuracy. It beats Muse Voice Transcribe (3.1% WER / 0.16s), Cartesia Ink-2 with semantic endpoints (3.4% WER / 0.43s), and ElevenLabs Scribe v2 Realtime (3.6% WER / 0.14s), trading some speed for accuracy.
Related event: xAI Launches Grok Voice Transcribe 2.0, Tops Streaming ASR Leaderboard(15 posts)→
More from Models
- Fable 5.5 delayed as Anthropic reportedly bets OpenAI's Astra 6.2 won't beat it — haider1 · 2026-11-04
- Community asks Moonshot when Kimi K3.1 model weights will drop — bgmshana · 2026-11-04
- Meta's Muse Spark Open license counts distilled models as derivatives — aidenclarke_12 · 2026-11-04
- Tencent Hy4 trails GPT-6.1 on hard tests as Kimi K3.1 Pro beats it on two benchmarks — heyshrutimishra · 2026-11-04
- Tencent's Hy4 agent self-trained a smaller model that beat Tencent's own baseline — heyshrutimishra · 2026-11-04
- Hy4 tops open models in finance eval at 3.04, hallucination rate cut to 5.45% — heyshrutimishra · 2026-11-04