Antonio Zugaldia
Antonio Zugaldia
@zugaldia.com
Building stuff, one thing at a time. Voice engineering at Mapbox. Former WHO and Silica Labs. Physicist. I have a bad feeling about this mission.
146 followers218 following103 posts
Antonio Zugaldia reposted
OK this piece by @reckless.bsky.social about why AI is unpopular among most people (anyone who's not inflicted with "software brain") is just solid gold from start to finish
THE PEOPLE DO NOT YEARN FOR AUTOMATION
That Kotlin library to interact with XDG Desktop Portals is the same speedofsound.io integrates under the hood!
Libadwaita demo app on Android, new update for Goblint, a linter for C GObject codebases, Java/Kotlin library for interacting with XDG Desktop Portal and much more in This Week in GNOME! #246 Offline Dictionaries thisweek.gnome.org/posts/2026/0... #ThisWeekInGNOME #GNOME #TWIG
Thank you @ubuntupit.bsky.social for the review!
A new Linux desktop application called Speed of Sound is making voice typing more practical. It uses modern speech recognition to convert spoken words into text across applications with a focus on speed, privacy, and offline usability. linuxnews.io/speed-of-sou...
New Speed of Sound v0.13 release is out! Added support for a system tray icon that works across distros, LLM providers get a Disable Thinking toggle to cut latency, a test connection button, plus the usual little improvements. You can download the app from Flathub and Snapcraft: www.speedofsound.io
Another write-up this week on Speed of Sound letsdatascience.com/news/speed-o...
Thank you @d0od.bsky.social for featuring Speed of Sound on @omgubuntu.co.uk ! Fun read and good motivation to get the new release out sooner than later. www.omgubuntu.co.uk/2026/04/spee...
New Speed of Sound release is out! You can now use NVIDIA Parakeet and Canary models for on-device transcription, alongside Whisper. More models = better accuracy across languages + more offline/private options. Flathub/Snapcraft links & install instructions on www.speedofsound.io/getting-star...
Great news: My little voice typing app for Linux is now available on both Flathub and Snapcraft. Links for both here: www.speedofsound.io/getting-star...
On unrelated news, you should read TWIG this week. I hear it comes with particularly good app announcements this week. thisweek.gnome.org//posts/2026/...
Instant pre-order. Love the form factor, and the hackability even more.
We just launched a new product - Pebble Index 01 It's a small ring, with a button and mic. Press the button, talk and it saves your thought. I use it many times during the day to jot down reminders, todos, book recs, etc while my hands are full. Just $75 - preorders on rePebble.com/index
Good move about the camera, bad move about the speaker www.zugaldia.com/notes/smart-...
Even Realities’ new smart glasses ditch cameras and speakers
Love this. It's a win-win, we listeners get no ads and the publisher gets a stickier subscription. If you're looking for another high quality podcast with a similar no ads option check out @latenightlinux.bsky.social .
The number one request we've gotten since we launched subscriptions was ad-free podcasts, and it took a lot of work but they are HERE. Sign up! www.theverge.com/bulletin/795...
@8none1.org I just heard your comment about voice being the future of typing in a recent LNL episode. And I agree 100%. That's why I built github.com/zugaldia/spe..., which I've been using daily for most of my typing for months now. Feedback/contributions always welcome.
DevFestDC is today! Find me to talk AI and @mapbox.com (and, oh yes, we're hiring).
My experience using the Meta Ray-Ban glasses for the last six months or so, where I make the case that audio, not vision, is the current killer feature for smart glasses: www.zugaldia.com/notes/smart-...
Antonio Zugaldia reposted
I designed the biggest binoculars in the world (that you can buy) and they're for looking at outer space 🔭 🌌. Early access is a big step for our nano-scale mom-and-pop business to bring this model to life! www.analogsky.co/bloom
My favorite use case is creating custom map styles, which I'm pretty bad at. “Create a Halloween-themed map. Make it look spooky and fun.”
Now, it’s faster and easier to build with Mapbox by equipping AI coding tools with access to the Mapbox platform. The Mapbox MCP DevKit provides an interface to help AI assistants like Copilot, Cursor, and Claude Code to understand and streamline the Mapbox development environment: a.mbx.io/45sUFrH
Great advice for LLMs in particular and life in general (context: news.ycombinator.com/item?id=4488...).
DevFestDC is back! In collaboration with @developers.google.com, this year we're running a one-day event themed around generative AI and emerging technologies. More information about tickets and how to apply to speak on www.devfestdc.org
Clear your LLM context early and often. www.science.org/content/arti...
This is very interesting. I particularly like the proposal under the hood for a lightweight mobile MCP implementation that is Android native.
🪿📱Introducing Goose Mobile An exciting new experimental project in the goose ecosystem! Goose Mobile is an open agent that runs directly on your Android device, designed to maximize automation of your everyday tasks. github.com/block/goose-...
Antonio Zugaldia reposted
Antonio Zugaldia reposted
Turn on the sound — this is how nearly every night sounds for me and my family. Imagine getting used to that, living, working, raising kids. A lesson the world didn’t learn from WW2: when you tolerate and appease evil, it grows stronger, and you won’t notice until it reaches your home.
Russia continues it ongoing campaign of terror against Ukrainian cities.
Love seeing this. There is a lot that can be done to improve the GNOME experience using the latest generative AI. Plenty of good local models to keep everything on device, and also cloud options when the use case requires it.
Something I’ve been looking for! 😍 #GNOME Desktop integration with LLMs through #MCP. belmoussaoui.com/blog/21-mcp-... Wouldn’t it be nice to check the possibility of using a different (more “open” and local) #LLM with vLLM or Ollama ? @gnomefoundation.bsky.social
So Agents success drops with the task length exponentially, like radioactive decay, BUT because of new model improvements, every 7 months the length of tasks AI agents can successfully complete *doubles*. www.tobyord.com/writing/half...
TIL claude.md redirects to the Claude Code docs. Nice one @anthropic.com.
Our MCP goes live! Reach out if you try it out and want to share any feedback.
Wish AI agents were better at reading maps? Now they can be! With access to the Mapbox MCP Server, any AI agent can generate maps, get directions, find points of interest, and more… 🤖🗺️💡 github.com/mapbox/mcp-s... #BuiltWithMapbox #LLM #MCP #AIAssistants #ModelContextProtocol @anthropic.com
Looks like Anthropic/Claude is giving up on TTS and relying on @elevenlabs.io for their recently announced voice mode. Interestingly, no mention of STT though. Source: app.vanta.com/anthropic/tr...
Interesting. Ollama is moving away from primarily using the llama.cpp project as a turnkey solution for model support, to building its own engine that leverages the underlying GGML library that llama.cpp uses. ollama.com/blog/multimo...
Antonio Zugaldia reposted
I am so impressed by the excitement for robotics all over the world! We are 1 month away of the global hackathon and already +1000 participants plan to team up at +80 locations 🤯 Be part of this special event by filling the form through this link: forms.gle/fYQteWn2R2D...
Amazing. Microsoft has managed to write an entire blog post about supporting a Google standard without mentioning Google a single time. www.microsoft.com/en-us/micros...