xAI Launches Grok Voice Think Fast 2.0 with Enhanced Noise Robustness and Reasoning
On July 30, xAI officially released the new end-to-end voice model Grok Voice Think Fast 2.0, designed specifically for voice agents in real-world physical environments, and simultaneously opened it to the API and Voice Agent Builder. The model features comprehensive upgrades in noise-resistant transcription, complex workflow reasoning, and natural conversation, with a time-to-first-audio under 1 second and API pricing at $0.08/minute ($4.80/hour).
Confirmed
- Noise Resistance and Transcription: In tests across 24 languages, its accuracy outperformed specialized models, and its noise resistance is 10 times that of specialized models.
- Benchmark Performance: According to Artificial Analysis, Grok Voice Think Fast 2.0 High ranks second (82.9%) on the Speech-to-Speech index and tops the agent performance benchmark τ-voice Bench with a score of 56.5%.
- Latency and Pricing: Time-to-first-audio is only 0.7 seconds; API pricing is $0.08 per minute, or $4.80 per hour of input audio. While this is an increase from the previous 1.0 version ($3.00/hour), it remains cheaper than similar real-time voice models like GPT (roughly half the price).
Why it matters
- This model directly targets voice interaction scenarios in complex real-world environments. Leveraging its exceptional noise resistance and low latency, it provides a new foundational infrastructure for building highly responsive voice agents. Its relatively developer-friendly API pricing also helps lower the cost barrier in the real-time voice application space.
2026-07-30 ~ 2026-07-30 · 15 related posts
Primary sources
- [source] xAI Launches Grok Voice 2.0: #2 in Speech-to-Speech, 0.70s Latency — ArtificialAnlys · 2026-07-30
- Grok Voice 2.0 Tops Tau Voice Benchmark with Massive Leaps in Full Duplex Scores — ArtificialAnlys · 2026-07-30
- Grok Voice 2.0 Priced at $4.80/Hour: Significantly Cheaper Than GPT — ArtificialAnlys · 2026-07-30
- Artificial Analysis Launches Comprehensive Speech-to-Speech AI Leaderboard — ArtificialAnlys · 2026-07-30
- [source] xAI Officially Announces Grok Voice Think Fast 2.0 — SpaceXAI · 2026-07-30
- [source] xAI Launches Grok Voice 2.0: Noise Robustness and Transcription Accuracy 10x Better than Dedicated Models — SpaceXAI · 2026-07-30
- Grok Voice 2.0 Hits API at $0.08/min with Upgraded Noise Robustness and Reasoning — SpaceXAI · 2026-07-30
- Grok Voice Think Fast 2.0 Released: Major Leaps in Voice Reasoning and Noise Robustness — XFreeze · 2026-07-30
- Grok Voice Think Fast 2.0 tops Artificial Analysis τ-Voice benchmark, excelling in real customer-service tasks — XFreeze · 2026-07-30
- xAI Announces Grok Voice Think Fast 2.0 with Improved Intelligence — kevinnbass · 2026-07-30
- Grok Voice 2.0 Details: 0.7s Latency, 60% Fewer Tokens at $0.08/min — mark_k · 2026-07-30
- xAI's Grok Voice Think Fast 2.0 Tops Speech-to-Speech Benchmark — elonmusk · 2026-07-30
3 near-duplicate retellings: ArtificialAnlys · ArtificialAnlys · XFreeze