Fixa – an open source Python package for testing voice agents
hey! this is oliver and jonathan and today, we’re launching fixa — a free, open source package to test voice agents. fixa uses a voice agent to call your voice agent and an LLM to evaluate how the conversation went. here's a demo: https://youtu.be/LAW1wW6SjTo this was initially a paid feature of our platform, but the monetization model didn't really make sense. our customers were paying us for all the components of our agent (STT + LLM + TTS + markup) in addition to their own agent – even though many of them have preferred vendors, volume discounts, and credits. we came to the…
In plain words
Fixa is an open source Python package that enables developers to test voice agents by having one voice agent call another and using an LLM to evaluate the conversation quality. Built for teams developing voice applications, it allows users to bring their own API keys for speech-to-text, language models, and text-to-speech components rather than paying for bundled services. The package is free to use and available on GitHub.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
hey! this is oliver and jonathan and today, we’re launching fixa — a free, open source package to test voice agents. fixa uses a voice agent to call your voice agent and an LLM to evaluate how the conversation went. here's a demo: https://youtu.be/LAW1wW6SjTo this was initially a paid feature of our platform, but the monetization model didn't really make sense. our customers were paying us for all the components of our agent (STT + LLM + TTS + markup) in addition to their own agent – even though many of them have preferred vendors, volume discounts, and credits. we came to the conclusion that you should be able to use your own API keys to test your own voice agents. e2e testing for web apps is done using free and open source packages (selenium, puppeteer), we think the same should be true for voice. running tests with fixa will always be free. we make money if you decide to use our cloud platform to visualize your test results. fixa is still in the early stages, so we would appreciate any and all feedback!
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, January 2025
the whole month →- IM
Hello! I'm Byran. I spent the past ~6 months engineering a laptop from scratch. It's fully open-source on GH at: https://github.com/Hello9999901/laptop
Dev tools · 2025 · byran.ee
- TITetris in a PDF▲1,289
I realized that the PDF engines of modern desktop browsers (PDFium and PDF.js) support JavaScript with enough I/O primitives to make a basic game like Tetris. It was a bit tricky to find a union of features that work in both engines, but in the end it turns out that showing/hiding annotation "fields" works well to make monochrome pixels, and keyboard input can be achieved by typing in a text input box. All in all it's quite janky but a nice reminder of how general purpose PDF scripting can be. The linked PDF is all ASCII so you can just open it in a text editor, or have a look at…
Life & fun · 2025 · th0mas.nl
Create lifelike, personalized AI avatars from text prompts
AI · 2025 · jogg.ai
