News for hackers. Stuff that matters.
Re:Show HN: I built a sub-500ms latency voice agent from scr... by docheinestages on Monday March 02, 2026 @05:58PM (#47225431)
Does anyone know about a fully offline, open-source project like this voice agent (i.e. STT -> LLM -> TTS)?
Re:Show HN: I built a sub-500ms latency voice agent from scr... by nicktikhonov on Monday March 02, 2026 @06:02PM (#47225480)
A friend built this, everything working in-browser:

https://ttslab.dev/voice-agent

Re:Show HN: I built a sub-500ms latency voice agent from scr... by numpad0 on Tuesday March 03, 2026 @06:45AM (#47231035)
This is hardly a novel implementation of [stream responses and chunk on sentences] + [stop on VAD and memory hole the chat log] concept. This takes <1k vibecoded lines to replicate it with an all-local setup.
Re:Show HN: I built a sub-500ms latency voice agent from scr... by nfrench17 on Tuesday March 03, 2026 @12:44PM (#47235964)
pipecat is the best! (imo) https://github.com/pipecat-ai/pipecat