Volodymyr Kuleshov 🇺🇦
@volokuleshov
🎙️ Announcing Mercury Voice, the newest model in the Mercury lineup
⚡ Powered by diffusion, it's the world's fastest LLM for real-time voice agents in customer support, sales, education & more
🏎️ Faster than Cerebras
🧠 Higher quality than frontier models
Give it a spin!
⚡ Powered by diffusion, it's the world's fastest LLM for real-time voice agents in customer support, sales, education & more
🏎️ Faster than Cerebras
🧠 Higher quality than frontier models
Give it a spin!
Inception@_inception_ai · Sep 29Today, we’re introducing Mercury Voice, a diffusion LLM specialized for agentic voice applications.
Mercury Voice delivers 2x+ lower latency than models including GPT-6 Luna, Gemma 4 31B, and Claude Haiku 4.5, while beating them on a range of voice benchmarks.
Enterprise
Mercury Voice delivers 2x+ lower latency than models including GPT-6 Luna, Gemma 4 31B, and Claude Haiku 4.5, while beating them on a range of voice benchmarks.
Enterprise
0:20 3 31