Hacker News Reader

rason-yangon Show HN: Jamb AI - Voice Agents for Group Calls

Do you send the model mixed audio or s separate track for everyone ? When people talk at the same time, how to speaker diarization ？

rason-yangon Show HN: AgentRun: DSL to turn agents into workflows

This matches how i think about realtime voice: keep call control deterministic, and give model steps clear inputs and outputs. How would you handle retries when a step fails ?

rason-yangon Show HN: Fluentry – local voice-to-text dictation for Linux, Wayland included

I build low-latency voice gateways . Does your local API expose interim transcripts and timestamps while audio is arriving , or only the final text after a dictation ends ?

rason-yangon Show HN: Suparelay – Call any phone in the world from a browser tab

i work on real-time voice AI systems. how does Tachyon handle cancellation and client disconnects for long-running MCP tools over Streamable HTTP?