Inception Labs' Mercury Voice Hits 320ms Response for Live AI Calls
Inception Labs' new diffusion-based model returns its first spoken token in 320ms median, finally fitting a reasoning model inside the 500ms voice budget.
Read the full story at AlphaSignal ↗
Timeline · 1 report
- 2026-09-29 16:39 · AlphaSignal
Inception Labs' Mercury Voice Hits 320ms Response for Live AI Calls