I built a sub-500ms latency voice agent from scratch
I built a voice agent from scratch that averages ~400ms end-to-end latency (phone stop → first syllable). That’s with full STT → LLM → TTS in the loop, clean barge-ins, and no precomputed responses. What moved the needle: Voice is a turn-taking problem, not a transcription problem. VAD alone fails; you need semantic end-of-turn detection. The system reduces to one loop: speaking vs listening. The two transitions - cancel instantly on barge-in, respond instantly on end-of-turn - define the experience. STT → LLM → TTS must stream. Sequential pipelines are dead on arrival for natural…
In plain words
A voice agent built from scratch that achieves approximately 400 milliseconds of end-to-end latency while running speech-to-text, language model, and text-to-speech in parallel. The system prioritizes turn-taking detection over transcription accuracy, enabling users to interrupt naturally with instant cancellation and immediate responses. It uses streaming architecture throughout the pipeline and colocates components to minimize latency. The builder emphasizes that semantic understanding of conversation turns, rather than voice activity detection alone, creates a natural conversational experience.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
I built a voice agent from scratch that averages ~400ms end-to-end latency (phone stop → first syllable). That’s with full STT → LLM → TTS in the loop, clean barge-ins, and no precomputed responses. What moved the needle: Voice is a turn-taking problem, not a transcription problem. VAD alone fails; you need semantic end-of-turn detection. The system reduces to one loop: speaking vs listening. The two transitions - cancel instantly on barge-in, respond instantly on end-of-turn - define the experience. STT → LLM → TTS must stream. Sequential pipelines are dead on arrival for natural conversation. TTFT dominates everything. In voice, the first token is the critical path. Groq’s ~80ms TTFT was the single biggest win. Geography matters more than prompts. Colocate everything or you lose before you start. GitHub Repo: https://github.com/NickTikhonov/shuo Follow whatever I next tinker with: https://x.com/nick_tikhonov
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
