https://openvoiceos.github.io/ovos-blogs 2026-10-05T00:22:26.266Z daily 1.0 https://openvoiceos.github.io/ovos-blogs/about 2026-10-05T00:22:26.266Z monthly 0.8 https://openvoiceos.github.io/ovos-blogs/archive 2026-10-02T00:00:00.000Z weekly 0.9 https://openvoiceos.github.io/ovos-blogs/feed.xml 2026-10-02T00:00:00.000Z daily 0.8 https://openvoiceos.github.io/ovos-blogs/posts/2026-10-02-wakeforge-wake-words 2026-10-05T00:21:49.655Z weekly 0.9 https://openvoiceos.github.io/ovos-blogs/assets/blog/wakeforge/thumb2.jpg How we distilled HuBERT into 1.22 MB for wake words HuBERT-base has about 95 million parameters. WakeHuBERT tiny, its streaming student, has about 0.64 million, and its int8 file gzips to 1.22 MB. Here is how we distilled it, and the new OVOS wake word plugin whose models run on it. https://openvoiceos.github.io/ovos-blogs/posts/2026-09-26-speaker-verifier 2026-10-05T00:21:49.655Z weekly 0.8 https://openvoiceos.github.io/ovos-blogs/assets/blog/speaker-verification/cover2.jpg Only you can order the cheeseburgers: Speaker verification comes to OVOS A new wake word verifier plugin teaches OpenVoiceOS to recognise *who* is speaking, not just *what* was said. Enrolled household voices get through the wake gate; the TV advert and the guest who thinks he's funny don't. https://openvoiceos.github.io/ovos-blogs/posts/2026-03-24-ovos-localize-github-native-translation 2026-10-05T00:21:49.654Z weekly 0.8 https://openvoiceos.github.io/ovos-blogs/assets/blog/ovos-localize/thumb.jpg OVOS Localize: The zero-maintenance translation platform on GitHub A full translation platform for OpenVoiceOS skills: context-aware editor, automated PR pipeline, a validation engine tuned to voice-assistant file types, and open ML datasets, running entirely on GitHub, with zero infrastructure of our own to operate. Just a GitHub account, and forkable by anyone. https://openvoiceos.github.io/ovos-blogs/posts/2026-07-22-from-one-fairytale-skill-to-a-whole-reading-pipeline 2026-10-05T00:21:49.654Z weekly 0.8 https://openvoiceos.github.io/ovos-blogs/assets/blog/from-one-fairytale-skill-to-a-whole-reading-pipeline/cover.jpg From one fairytale skill to a full reading pipeline plug-in How a 2018 Mycroft fairytale skill, two false starts, and one offhand comment from Jarbas turned into an 8-provider common-reading pipeline for OVOS. https://openvoiceos.github.io/ovos-blogs/posts/2026-08-02-porting-with-machines 2026-10-05T00:21:49.655Z monthly 0.7 https://openvoiceos.github.io/ovos-blogs/assets/blog/porting-with-machines/cover.png Porting With Machines, and the Licence Question We Could Not Answer We rewrote several C, C++ and Java programs (espeak-ng's G2P, Cotovia, AhoTTS, HermiT) as pure Python, with an AI reading the original source and a human orchestrating. No human on our side read the originals. That raises two separate questions: can the output be owned at all, and is it a derivative of the input? We kept the upstream licences because that was cheaper than answering. We still think the question is open. https://openvoiceos.github.io/ovos-blogs/posts/2026-07-24-a-terminal-client-for-testing-ovos 2026-10-05T00:21:49.655Z monthly 0.7 https://openvoiceos.github.io/ovos-blogs/assets/blog/a-terminal-client-for-testing-ovos/cover.png The Terminal Client OVOS Was Missing Why I built a TUI client for testing OVOS without a mic or speaker - and a few real bugs it caught along the way that no amount of log-tailing would have surfaced on its own. https://openvoiceos.github.io/ovos-blogs/posts/2026-07-15-mcp-utcp-speech-servers 2026-10-05T00:21:49.654Z monthly 0.7 https://openvoiceos.github.io/ovos-blogs/assets/blog/ngi/thumb.png Call OVOS Speech Servers From Any AI Agent OVOS STT, TTS, and translation servers now describe themselves over UTCP and mount an MCP endpoint. Any agent that speaks either protocol can discover and call them — no custom client, no wrapper code. https://openvoiceos.github.io/ovos-blogs/posts/2026-03-05-ovos-installer-macos-intel-apple-silicon 2026-10-05T00:21:49.654Z monthly 0.6 https://openvoiceos.github.io/ovos-blogs/assets/blog/ovos-installer-macos/ovos-installer-macos-support.png Boring installs, now on macOS: ovos-installer supports Intel + Apple Silicon ovos-installer can now deploy OpenVoiceOS on macOS (Intel and Apple Silicon) using launchd + virtualenv. Here’s the boring (good) path to a working OVOS stack on your Mac. https://openvoiceos.github.io/ovos-blogs/posts/2026-02-16-onnx-asr 2026-10-05T00:21:49.654Z monthly 0.6 https://openvoiceos.github.io/ovos-blogs/assets/blog/onnx-asr/thumb.png Bringing Real-Time Offline Speech Recognition to OpenVoiceOS ONNX, New Plugins, and the Road Here. https://openvoiceos.github.io/ovos-blogs/posts/2026-02-05-OpenVoiceOS-Speechday-2026 2026-10-05T00:21:49.654Z monthly 0.6 https://openvoiceos.github.io/ovos-blogs/assets/blog/OpenVoiceOS-Speechday-2026/sound-and-vision-main-venue.jpg OpenVoice OS @ Speechday 2026 A recap of our visit to the fourth Dutch Speech Tech Day in Hilversum, the Netherlands https://openvoiceos.github.io/ovos-blogs/posts/2026-01-25-voice-first 2026-10-05T00:21:49.654Z monthly 0.6 https://openvoiceos.github.io/ovos-blogs/assets/blog/voice-faster-than-typing/cover.png Voice: 5× Faster Than Typing and ready for the AI era We still type, click, and scroll, even though speaking is the fastest, most natural interface humans have ever had. Voice isn’t a gimmick. It’s the interface AI has been waiting for. https://openvoiceos.github.io/ovos-blogs/posts/2026-01-14-OVOS-hivemind-industry 2026-10-05T00:21:49.654Z monthly 0.6 https://openvoiceos.github.io/ovos-blogs/assets/blog/ovos-hivemind-industry/thumb.png OVOS & HiveMind in the Manufacturing Industry The COALA and WASABI EU projects have built an entire industrial voice-assistant framework around OVOS + HiveMind, integrating them with their own tools, UI, and conversation engines. https://openvoiceos.github.io/ovos-blogs/posts/2025-12-14-barranquenho 2026-10-05T00:21:49.654Z monthly 0.6 https://openvoiceos.github.io/ovos-blogs/assets/blog/barranquenho/thumb.png Introducing the First Phonemizer for Barranquenho Today marks an exciting milestone for linguistic preservation! We're thrilled to announce the development of the very first phonemizer for Barranquenho, a truly unique Ibero-Romance language spoken in the Portuguese municipality of Barrancos. https://openvoiceos.github.io/ovos-blogs/posts/2025-12-09-ast 2026-10-05T00:21:49.654Z monthly 0.6 https://openvoiceos.github.io/ovos-blogs/assets/blog/ast/thumb.png Cloning Voices for Endangered Languages: Building a Text-to-Speech Model for Asturian and Aragonese Have you ever wanted to hear a computer speak in an accent you love, or in a language that's rarely supported by big tech? Today we’re releasing new experimental Text-to-Speech models for Asturian (ast) and Aragonese (an), two beautiful minority Romance language spoken by communities who almost never get access to modern speech technology. https://openvoiceos.github.io/ovos-blogs/posts/2025-11-25-gofai 2026-10-05T00:21:49.654Z monthly 0.6 https://openvoiceos.github.io/ovos-blogs/assets/blog/gofai/thumb.jpg Good Old-Fashioned AI: The Secret Ingredient in a Modern Voice Assistant In an era dominated by probabilistic giants like Large Language Models (LLMs), it might seem counterintuitive to advocate for a more traditional approach to Artificial Intelligence. https://openvoiceos.github.io/ovos-blogs/posts/2025-11-06-prewake-vad 2026-10-05T00:21:49.654Z monthly 0.6 https://openvoiceos.github.io/ovos-blogs/assets/blog/prewake-vad/thumb.png OVOS Just Got a Noise Filter: Better Listening, Less Interruption We're thrilled to announce a new feature in OpenVoiceOS that aims to improve how your device listens. This new logic improves performance, reduces false activations, and makes OVOS an even more delightful and reliable voice assistant https://openvoiceos.github.io/ovos-blogs/posts/2025-11-03-precise-onnx 2026-10-05T00:21:49.654Z monthly 0.6 https://openvoiceos.github.io/ovos-blogs/assets/blog/precise_onnx/thumb.png Precise Wake Word Engine Goes ONNX! For years, the OpenVoiceOS community has relied on the Precise wake word engine. It's the core of how you bring your voice assistant to life! However, as technology evolves, so must we. The time has come to ensure future compatibility and even better performance on modern hardware. https://openvoiceos.github.io/ovos-blogs/posts/2025-10-24-protocol_interoperability 2026-10-05T00:21:49.654Z monthly 0.6 https://openvoiceos.github.io/ovos-blogs/assets/blog/protocol_interoperability/thumb.png Building an Open and Interoperable Voice Ecosystem OpenVoiceOS has always been about freedom and flexibility, giving users full control over their voice assistants and how they connect with the world. But freedom also brings a challenge: ensuring that all these independent components can understand and work with each other. https://openvoiceos.github.io/ovos-blogs/posts/2025-10-20-ngi 2026-10-05T00:21:49.653Z monthly 0.6 https://openvoiceos.github.io/ovos-blogs/assets/blog/ngi/thumb.png OpenVoiceOS Receives NGI Zero Commons Fund Grant We’re excited to share some fantastic news — OpenVoiceOS has been selected to receive a grant from the NGI Zero Commons Fund! https://openvoiceos.github.io/ovos-blogs/posts/2025-10-18-rss 2026-10-05T00:21:49.653Z monthly 0.6 https://openvoiceos.github.io/ovos-blogs/assets/blog/rss/thumb.png OpenVoiceOS Blog Launches RSS Feed — A Win for Accessibility & Open Standards We’re happy to announce that the OpenVoiceOS blog now supports a RSS/Atom feed https://openvoiceos.github.io/ovos-blogs/posts/2025-10-11-r36s 2026-10-05T00:21:49.653Z monthly 0.6 https://openvoiceos.github.io/ovos-blogs/assets/blog/r36s/thumb.png Running HiveMind Player on ArkOS with the R36S The R36S handheld from AliExpress is usually marketed as a retro gaming device, but with a bit of tinkering it can also become a HiveMind-powered audio player, fully integrated with Home Assistant and Music Assistant https://openvoiceos.github.io/ovos-blogs/posts/2025-10-06-phoonnx 2026-10-05T00:21:49.653Z monthly 0.6 https://openvoiceos.github.io/ovos-blogs/assets/blog/phoonnx/thumb.png Introducing phoonnx: The Next Generation of Open Voice for OpenVoiceOS Today marks a significant step forward in the OpenVoiceOS journey with the official integration and adoption of phoonnx as our primary Text-to-Speech (TTS) engine. https://openvoiceos.github.io/ovos-blogs/posts/2025-10-01-arabic_tts_collaboration 2026-10-05T00:21:49.653Z monthly 0.6 https://openvoiceos.github.io/ovos-blogs/assets/blog/arabic_tts_collaboration/thumb.png Voices of Inclusion: Reflections on Our Collaboration As the External Collaborations Lead at Planet Blind Tech, I recently had the privilege of working closely with OpenVoiceOS on a groundbreaking project: training an open-source Arabic voice. https://openvoiceos.github.io/ovos-blogs/posts/2025-09-17-ovos_ha_dream_team 2026-10-05T00:21:49.653Z monthly 0.6 https://openvoiceos.github.io/ovos-blogs/assets/blog/OpenVoiceOS-and-Home-Assistant-a-voice-automation-dream-team/thumb.png OpenVoiceOS and Home Assistant: A Voice Automation Dream Team In the world of open-source smart homes, some things just click. When you let Home Assistant handle the automation and let OVOS (Open Voice OS) handle the voice, you get a powerful partnership where each project shines. It’s a perfect synergy https://openvoiceos.github.io/ovos-blogs/posts/2025-08-23-enhance-magicmirror-with-ovos 2026-10-05T00:21:49.653Z monthly 0.6 https://openvoiceos.github.io/ovos-blogs/assets/blog/enhance-magicmirror-with-ovos/thumbnail.png Mirror, Mirror… Who’s My Persona Today? (OVOS + MagicMirror² + Local LLM) Daily-driver setup: keep skills first, add OVOS Persona right after the high-confidence matchers, and run a tiny local LLM. MagicMirror² shows the vibes with wakeword visuals and YouTube casting. https://openvoiceos.github.io/ovos-blogs/posts/2025-07-25-A-real-use-case-with-OVOS-and-Hivemind 2026-10-05T00:21:49.653Z monthly 0.6 https://openvoiceos.github.io/ovos-blogs/assets/blog/A-real-use-case-with-OVOS-and-Hivemind/Thumbnail_3D_case.jpg A real use case with OVOS and Hivemind A practical example of OVOS and Hivemind running locally on standard hardware, designed for home automation and basic AI assistant tasks — especially suited for supporting people with disabilities. https://openvoiceos.github.io/ovos-blogs/posts/2025-07-22-ovos-transcription-validator-plugin 2026-10-05T00:21:49.653Z monthly 0.6 https://openvoiceos.github.io/ovos-blogshttps://raw.githubusercontent.com/OpenVoiceOS/ovos_assets/refs/heads/master/OVOS_transcript_Validator.png No More Mumbo Jumbo: Meet the OVOS Transcription Validator Plugin Ever had your beloved OpenVoiceOS assistant respond with a blank stare, or worse, utter something completely nonsensical, after you *thought* you said something perfectly clear? We've all been there. https://openvoiceos.github.io/ovos-blogs/posts/2025-06-26-making-synthetic-voices-from-scratch 2026-10-05T00:21:49.653Z monthly 0.6 https://openvoiceos.github.io/ovos-blogshttps://github.com/OpenVoiceOS/ovos_assets/blob/master/ovos_tts.png?raw=true Making Synthetic Voices From Scratch Creating a voice for a text-to-speech system usually requires a real person to spend hours recording audio. That’s expensive, time-consuming, and in many languages or accents, the voices just don’t exist at all https://openvoiceos.github.io/ovos-blogs/posts/2025-05-20-ovos-and-mycroft-a-fork-that-wasnt-meant-to-be 2026-10-05T00:21:49.653Z monthly 0.6 https://openvoiceos.github.io/ovos-blogs/assets/blog/common/cover.png OVOS and Mycroft: A Fork That Wasn't Meant to Be How OpenVoiceOS emerged not as a rebellious fork but as a necessary continuation of the Mycroft project, driven by the core community to create a truly open voice assistant. https://openvoiceos.github.io/ovos-blogs/posts/2025-05-06-when-your-voice-assistant-becomes-a-persona 2026-10-05T00:21:49.653Z monthly 0.6 https://openvoiceos.github.io/ovos-blogs/assets/blog/common/cover.png When Your Voice Assistant Becomes a Persona: The Power and Peril of LLMs in OpenVoiceOS The latest evolution of OpenVoiceOS integrates LLMs through the Persona Pipeline, creating more human-like interactions, but not without psychological risks. https://openvoiceos.github.io/ovos-blogs/posts/2023-05-02-openvoiceos-now-available-on-containers 2026-10-05T00:21:49.653Z monthly 0.6 https://openvoiceos.github.io/ovos-blogs/assets/blog/common/cover.png OpenVoiceOS now available on containers Learn how OpenVoiceOS is now available as containerized services for easier installation and management. https://openvoiceos.github.io/ovos-blogs/posts/2023-03-21-campaign-update-new-goals 2026-10-05T00:21:49.653Z monthly 0.6 https://openvoiceos.github.io/ovos-blogs/assets/blog/common/cover.png Campaign Update: New Goals We are excited to announce our goal of €4,000 has been achieved! We are thrilled to have reached our goal, as it will help enable us to become a fully realized non-profit. https://openvoiceos.github.io/ovos-blogs/posts/2023-02-28-giving-voice-to-the-future-support-openvoiceos-in-establishing-a-nonprofit-association 2026-10-05T00:21:49.653Z monthly 0.6 https://openvoiceos.github.io/ovos-blogs/assets/blog/common/cover.png Giving Voice to the Future: Support OpenVoiceOS in Establishing a Nonprofit Association Learn how you can support OpenVoiceOS in establishing a nonprofit association to ensure the future of their open-source voice assistant projects. https://openvoiceos.github.io/ovos-blogs/posts/2023-02-28-permissive-licenses 2026-10-05T00:21:49.653Z monthly 0.6 https://openvoiceos.github.io/ovos-blogs/assets/blog/common/cover.png Why OpenVoiceOS Uses Permissive Licenses Explaining the license chosen for OVOS and what that entails for developers and users alike. https://openvoiceos.github.io/ovos-blogs/posts/2023-02-15-a-brief-history-of-open-voice-os 2026-10-05T00:21:49.653Z monthly 0.6 https://openvoiceos.github.io/ovos-blogs/assets/blog/common/cover.png A Brief History of Open Voice OS Explore the history of Open Voice OS, from its roots in MycroftAI to becoming a leading open-source voice assistant system.