PolyAI unveils Dialog-RSN-1: audio-native voice model answering in under 300ms
matthen2 · x · 2026-10-23
PolyAI released Dialog-RSN-1, a voice dialog model that hears caller audio directly and handles a full turn in a single pass — no separate speech-recognition step — responding in under 300ms (sub-1-second reply on live calls). Independent benchmarking by Coval found it the strongest realtime model tested on production-style calls, addressing the classic "hello, is anyone there?" latency problem. The team will host a Nov 4 webinar covering turn-taking, noise handling, and interruptions.
More from coding & agent
- Garry Tan endorses Aside Browser as the fix for agents getting blocked on the web — garrytan · 2026-10-23
- MCP server turned rogue 30 days after approval, prompting open-source mcp-guard lockfile tool — ErgoniaWorks · 2026-10-23
- Test: Coding Agents Won't Use an MCP Tool Unless AGENTS.md Mentions It — colinmcnamara · 2026-10-23
- Open-Source Tennis Models Plus Claude Turn Video Into a World-Class Coach — tweetsatpreet · 2026-10-23
- awesome-ai-apps: 132 Free Open-Source AI Agent and RAG Projects on GitHub — Arindam_1729 · 2026-10-23
- Google's Agents CLI Adds Extension System, Ships First-Party LangChain Support — rseroter · 2026-10-23