xAI Launches Grok Voice 2.0: Noise Robustness and Transcription Accuracy 10x Better than Dedicated Models
SpaceXAI · x · 2026-07-30
xAI officially announced the release of Grok Voice Think Fast 2.0, its next-generation speech-to-speech model. The model features comprehensive upgrades in intelligence, transcription accuracy, and conversational capabilities.
Key Highlights:
- Noise Robustness & Transcription: Outperforms dedicated models like Deepgram Nova 3 and ElevenLabs Scribe v2 by 1.5–2.0× in accuracy across 24 languages. In noisy settings, this lead widens to 10×.
- Benchmarks: Scores 82.9% on the AA Speech-to-Speech Quality Index. Full Duplex Bench score jumped from 77.8% to 95.1%.
- Speed: Time to First Audio (TTFA) significantly reduced from 1.25s to 0.70s.
- Reasoning Efficiency: Maintains its unique reasoning efficiency, offering better reliability in complex voice workflows and tool usage.
Related event: xAI Releases Grok Voice 2.0, Tops Voice Agent Benchmarks(20 posts)→
More from Models
- Why are sub-15B open models so rare now? Labs seem to have settled on 24-27B minimum — Hot_Example_4456 · 2026-10-16
- User spots model openly generating "ideal responses" to train other models — liminal_bardo · 2026-10-16
- Reflection's 501B MoE Beam hits 463 tok/s on 8x GB200 with NVFP4 at day 0 — zhyncs42 · 2026-10-16
- Gemma 4 31B QAT on one 24GB card: 46 tok/s plain, ~80 with draft model on RTX 4090 — Subject_Poet_3861 · 2026-10-16
- JevBench v1.7.46 leaderboard: new d1-ultra tops 32 API systems at 76.1 composite — airesearch12 · 2026-10-16
- Team of 5 mulls dropping ChatGPT Pro for Business as OpenAI quota parity stays unclear — bettercallfool · 2026-10-16