100% open-source voice assistant – as a HAL9000
It started in 2018 with my first 3D printer and some openscad designs - just something that looks like a HAL9000 (and had a controlled red LED for the visuals) - it ended up being a full software-project...that hasn't ended yet. But: it is at a (quality-)point at which I am OK with putting it up on stage. My project goals: A digital voice-assistant that is... - actually usable (response times, error rates, ...) - performs everything on-device ("look ma, no cloud") - is entirely Free/Libre Open-Source-Software - is as-easy-as-possible to build I consider all four goals to be accomplished…
In plain words
This project is an open-source voice assistant designed to resemble HAL9000, offering fully on-device processing without cloud dependency. Built entirely with free and open-source software, it prioritizes usability with fast response times and low error rates, while remaining relatively simple to construct. The assistant handles voice interactions locally, making it suitable for users prioritizing privacy and self-sufficiency. Development began in 2018 and reached a stable quality level suitable for public release.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
It started in 2018 with my first 3D printer and some openscad designs - just something that looks like a HAL9000 (and had a controlled red LED for the visuals) - it ended up being a full software-project...that hasn't ended yet. But: it is at a (quality-)point at which I am OK with putting it up on stage. My project goals: A digital voice-assistant that is... - actually usable (response times, error rates, ...) - performs everything on-device ("look ma, no cloud") - is entirely Free/Libre Open-Source-Software - is as-easy-as-possible to build I consider all four goals to be accomplished even at this ~90% stage of the project. If you just want to get some quick impressions, check out the "Demos" (video-)page in the github wiki (prominently linked in the README in the github repo). If you want to spend some more time on this, it's probably easiest to watch my presentation at Hackaday Europe from two months ago: https://www.youtube.com/watch?v=oqJCU8FRMQg&t=14761s
Does the same job
all alternatives →- AFA fast OSS voice assistant2024 · swift-ai.vercel.app · ▲82
- WOWhispering – Open-source, local-first dictation you can trust2025 · github.com · ▲591
Hey HN! Braden here, creator of Whispering, an open-source speech-to-text app. I really like dictation. For years, I relied on transcription tools that were almost good, but they were all closed-source. Even a lot of them that claimed to be “local” or “on-device” were still black boxes that left me wondering where my audio really went. So I built Whispering. It’s open-source, local-first, and most importantly, transparent with your data. Your data is stored locally on your device, and your audio goes directly from your machine to a local provider (Whisper C++, Speaches, etc.) or your chosen…
- AOAn open source framework for voice assistants2024 · github.com · ▲346
I've been obsessed for the past ~year with the possibilities of talking to LLMs. I built a bunch of one-off prototypes, shared code on X, started a Meetup group in SF, and co-hosted a big hackathon. It turns out that there are a few low-level problems that everybody building conversational/real-time AI needs to solve on the way to building/shipping something that works well: low-latency media transport, echo cancellation, voice activity detection, phrase endpointing, pipelining data between models/services, handling voice interruptions, swapping out different…
- IMI made an open source and local translation app2024 · github.com · ▲236
A few years ago, right after high school, I decided to try to make a simultaneous translation app for Android as a side project, it took longer than expected (about 2 years) and I had to make a lot of compromises (I had to use Google's API and therefore make users use a developer key because at the time there were no free solutions for speech recognition and translation that had good quality). At the end of university, I decided to pick it up again and finally, using OpenAi's Whisper for speech recognition and Meta's NLLB for translation (with both running locally on the phone), I managed to…
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, June 2024
the whole month →
La Growth Machine▲1,216Create personalized, multi-channel conversations at scale
AI · 2024 · lagrowthmachine.com
PyjamaHR▲1,132Hiring on autopilot. The AI applicant tracking system (ATS).
Work · 2024 · pyjamahr.com