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…
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 (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 different scenarios to make sure it wouldn’t break. Elixir makes this process 10x faster - we help you simulate 1000s of realistic test calls, automatically identify & triage “bad” conversations, and debug issues with audio snippets, call transcripts, and LLM traces all in one platform. Here’s the link - tryelixir.ai (sign up to try it out!). With multimodal models like GPT4o right around the corner, we believe voice agents will grow in capability and complexity, making testing and call review even more important for conversational reliability. We’re excited for you to try it out and are looking forward to hearing your feedback in the comments!
Does the same job
all alternatives →- IBI built a sub-500ms latency voice agent from scratchMar 2026 · ntik.me · ▲570
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…
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 · 27d ago · cactuscompute.com
Launched alongside, August 2024
the whole month →
- IY
Life & fun · 2024 · ytch.xyz
- IA
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