Grok Voice 2.0 Details: 0.7s Latency, 60% Fewer Tokens at $0.08/min
mark_k · x · 2026-07-30
Detailed breakdown of the Grok Voice Think Fast 2.0 upgrade:
- Top Performance: Scores 82.9% on the Artificial Analysis Speech-to-Speech Quality Index.
- Lower Latency: Cuts time to first audio from 1.25s to just 0.70s.
- Better Transcription: Major improvements in noisy real-world environments.
- Efficiency: Reasons while speaking using 60% fewer reasoning tokens and executes tool calls faster.
- Natural Interaction: Communicates more naturally with shorter answers and less fluff.
- Pricing: Available for $0.08 per minute.
More from Models
- Users Excited as Opus 5 is 'Cooking' with Impressive Capabilities — chrisfirst · 2026-07-30
- Claude Base Model Leaking Inner Thoughts? It's Just User Modeling — cephaloform · 2026-07-30
- Claude Experiences Major Service Outage, Disrupting Access — Polymarket · 2026-07-30
- Prediction Market: OpenAI Leads Odds for #1 AI Model by Year-End, Meta Trails at 12% — Polymarket · 2026-07-30
- Expert Clarifies: Kimi K3 'Self-Iteration' is Just Agent Harness Optimization, Not Model Evolution — dotey · 2026-07-30
- Third-Party Devs Boost Kimi K3 Inference to Nearly 80 TPS, Beating Official API — bittingthembits · 2026-07-30