xAI Launches Grok Voice Think Fast 1.0 API for Real-Time Voice Agents
Real-time voice model clones any voice from just 3 seconds of audio...
Deep Dive
xAI unveiled Grok Voice Think Fast 1.0 on April 30, 2026—its most advanced voice agent, now accessible via API. The real-time voice model helps businesses automate complex workflows and clone custom voices from short recordings.
Key Points
- Sub-200ms real-time speech-to-speech latency for natural conversations
- Custom voice cloning from just 3 seconds of audio with 95% acoustic accuracy
- Priced at $0.08/min base, $0.15/min with voice cloning, supports 29 languages
Why It Matters
Grok Voice API commoditizes real-time voice AI with cloning—now any business can build branded, human-like voice agents.