Testing voice AI and listening to calls takes time, so we automated it
Hey HN! I’m Akshay, and I built Elixir with my good friends, Chetan and Andrew. Elixir ensures your voice agent is reliable and works as expected in production through automated testing and call review. We built Elixir while trying to solve some of our own problems when building CodeCoach (https://www.trycodecoach.com/), an AI technical interviewer. We found ourselves spending significant time manually listening to calls for issues ranging from interruptions and transcription errors to user frustrations and poor conversation experiences, as well as trying to test the agent on…
Testing voice AI and listening to calls takes time, so we automated it launched on August 19, 2024 with 7 votes, #2,085 of 5,471 launches that month and more than 75% of that year's launches.
What it does
In the maker’s words, at launch
Hey HN! I’m Akshay, and I built Elixir with my good friends, Chetan and Andrew. Elixir ensures your voice agent is reliable and works as expected in production through automated testing and call review. We built Elixir while trying to solve some of our own problems when building CodeCoach…
Does a similar job
all alternatives →
I built a sub-500ms latency voice agent from scratchMar 2026 · ntik.me · ▲570I 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…
Voicebun2025 · voicebun.com · ▲189Hey HN, I built Voicebun as a pet project because I was frustrated with how locked-down and rigid voice agents still are—many tools are either closed platforms, lack deep customization, or charge a lot just to test ideas. I wanted a way to quickly spin up AI voice agents that I could fully control—from the voice itself to the logic behind every word. Voicebun is an open-source voice agent builder. You can: - Clone voices and generate audio using your own scripts and prompts - Dynamically change prompts based on user input - Add custom logic through functions and webhooks (e.g. hit an API,…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 22d ago · stillwet.art
FastRouter.ai▲364Route requests to the right LLM for cost, latency & quality
AI · 23d ago · fastrouter.ai
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, August 2024
the whole month →
Jupitrr AI▲1,195Jupitrr AI turns raw talking videos into scroll-stopping content for coaches and consultants. Research, script, record, edit, and publish in one app.
AI · 2024 · jupitrr.com
Hey there HN! We’re Joe and Stopa, and today we’re open sourcing InstantDB, a client-side database that makes it easy to build real-time and collaborative apps like Notion and Figma. Building modern apps these days involves a lot of schleps. For a basic CRUD app you need to spin up servers, wire up endpoints, integrate auth, add permissions, and then marshal data from the backend to the frontend and back again. If you want to deliver a buttery smooth user experience, you’ll need to add optimistic updates and rollbacks. We do these steps over and over for every feature we build, which can…
Dev tools · 2024 · github.com