Sign in

Antonio Zugaldia

@zugaldia.com
141 followers 215 following 103 posts

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.

PostsRepliesMedia
Antonio Zugaldia @zugaldia.com · 23/09/2026
"And when you let someone else dictate what appears on your screen, it’s the same as giving them the key to your brain."
000
Antonio Zugaldia @zugaldia.com · 26/04/2026
This one is worth listening and relistening.
000
Reposted by Antonio Zugaldia
Simon Willison @simonwillison.net · 24/04/2026
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
1844683
Antonio Zugaldia @zugaldia.com · 25/04/2026
That Kotlin library to interact with XDG Desktop Portals is the same speedofsound.io integrates under the hood!
000
Antonio Zugaldia @zugaldia.com · 22/04/2026
Thank you @ubuntupit.bsky.social for the review!
000
Antonio Zugaldia @zugaldia.com · 22/04/2026
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
speedofsound.io
Speed of Sound
Voice typing for the Linux desktop
010
Antonio Zugaldia @zugaldia.com · 22/04/2026
Another write-up this week on Speed of Sound letsdatascience.com/news/speed-o...
letsdatascience.com
000
Antonio Zugaldia @zugaldia.com · 21/04/2026
Now we're talking.
010
Antonio Zugaldia @zugaldia.com · 20/04/2026
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...
omgubuntu.co.uk
Type with your voice on Linux using this Whisper-based app - OMG! Ubuntu
Your mouth can (probably) say things quicker than your hands can type, yet voice typing is rarely used as a primary input method on desktop – yet most of
020
Antonio Zugaldia @zugaldia.com · 11/04/2026
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...
NVIDIA Parakeet and Canary models now available on Speed of Sound.
000
Antonio Zugaldia @zugaldia.com · 04/04/2026
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...
141
Antonio Zugaldia @zugaldia.com · 03/02/2026
NEVER FORGET.
000
Antonio Zugaldia @zugaldia.com · 09/12/2025
Instant pre-order. Love the form factor, and the hackability even more.
030
Antonio Zugaldia @zugaldia.com · 28/11/2025
@technologyreview.com is the new @wired.com.
000
Antonio Zugaldia @zugaldia.com · 15/11/2025
Good move about the camera, bad move about the speaker www.zugaldia.com/notes/smart-...
zugaldia.com
Meta Ray-Ban: Good speakers disguised as glasses - Antonio Zugaldia
Homepage and Notes
000
Antonio Zugaldia @zugaldia.com · 15/10/2025
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 .
010
Antonio Zugaldia @zugaldia.com · 12/10/2025
@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.
github.com
GitHub - zugaldia/speedofsound: Voice typing for the Linux desktop.
Voice typing for the Linux desktop. Contribute to zugaldia/speedofsound development by creating an account on GitHub.
131
Antonio Zugaldia @zugaldia.com · 03/10/2025
DevFestDC is today! Find me to talk AI and @mapbox.com (and, oh yes, we're hiring).
110
Antonio Zugaldia @zugaldia.com · 21/09/2025
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-...
zugaldia.com
Meta Ray-Ban: Great speakers disguised as glasses - Antonio Zugaldia
Homepage and Notes
000
Antonio Zugaldia @zugaldia.com · 16/09/2025
I'm ready to throw some money at whoever is printing t-shirts with that ultrathink design.
000
Antonio Zugaldia @zugaldia.com · 08/09/2025
I'll be introducing our new Feedback Agent later today @ 12.30 PST, ping/DM me here if you have any questions!
000
Antonio Zugaldia @zugaldia.com · 02/09/2025
> and says it has a $5B+ revenue run-rate (Anthropic) And about half of that is me paying for Claude Code.
010
Reposted by Antonio Zugaldia
Robert Asumendi @robertasumendi.bsky.social · 26/08/2025
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
analogsky.co
World's Biggest Binocular Telescope Model. 8" / 200mm Binoculars — Analog Sky
Analog Sky Bloom 8" reverse Newtonian binocular telescope gives you the most immersive views of the cosmos. Smart electronics combine with thoughtful design to create a whole new stargazing experience...
074
Antonio Zugaldia @zugaldia.com · 13/08/2025
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.”
000
Antonio Zugaldia @zugaldia.com · 13/08/2025
Great advice for LLMs in particular and life in general (context: news.ycombinator.com/item?id=4488...).
I've spent a lot of time trying to get LLM to generate things in a specific way, the biggest take away I have is, if you tell it "don't do xyz" it will always have in the back of its mind "do xyz" and any chance it gets it will take to "do xyz". When working on art projects, my trick is to specifically give all feedback constructively, carefully avoiding framing things in terms of the inverse or parts to remove.
100
Antonio Zugaldia @zugaldia.com · 13/08/2025
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
010
Antonio Zugaldia @zugaldia.com · 29/07/2025
Clear your LLM context early and often. www.science.org/content/arti...
000
Antonio Zugaldia @zugaldia.com · 21/07/2025
This is very interesting. I particularly like the proposal under the hood for a lightweight mobile MCP implementation that is Android native.
010
Reposted by Antonio Zugaldia
Zach Israel @zachisrael.bsky.social · 14/07/2025
I’m still in disbelief that *two-thirds* of the DC Council voted today to fully fund ranked-choice voting in the District beginning in June 2026! What an amazing day for local democracy! And a huge shoutout to every single DC resident who worked toward this moment.
072
Reposted by Antonio Zugaldia
Volodymyr Agafonkin @agafonkin.com · 10/07/2025
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.
042
Antonio Zugaldia @zugaldia.com · 09/07/2025
Oh this is gonna be fun. Ordered.
020
Antonio Zugaldia @zugaldia.com · 05/07/2025
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.
010
Antonio Zugaldia @zugaldia.com · 26/06/2025
This one is a no brainer for me, I've been getting value from GNOME for *decades* at this point, and for decades to come I hope.
133
Antonio Zugaldia @zugaldia.com · 18/06/2025
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...
tobyord.com
Is there a Half-Life for the Success Rates of AI Agents? — Toby Ord
Building on the recent empirical work of Kwa et al. (2025), I show that within their suite of research-engineering tasks the performance of AI agents on longer-duration tasks can be explained by an ex...
110
Antonio Zugaldia @zugaldia.com · 12/06/2025
TIL claude.md redirects to the Claude Code docs. Nice one @anthropic.com.
claude.md
Claude Code overview - Anthropic
Learn about Claude Code, an agentic coding tool made by Anthropic.
010
Antonio Zugaldia @zugaldia.com · 11/06/2025
Our MCP goes live! Reach out if you try it out and want to share any feedback.
101
Antonio Zugaldia @zugaldia.com · 08/06/2025
TIL YouTube thumbnail designer is a *full-time* job.
000
Antonio Zugaldia @zugaldia.com · 08/06/2025
I now have Copilot reviewing Claude Code PRs. What a time to be alive.
010
Antonio Zugaldia @zugaldia.com · 30/05/2025
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...
000
Antonio Zugaldia @zugaldia.com · 16/05/2025
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...
ollama.com
Ollama's new engine for multimodal models · Ollama Blog
Ollama now supports new multimodal models with its new engine.
100
Reposted by Antonio Zugaldia
Remi Cadene @remicadene.bsky.social · 12/05/2025
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...
091
Antonio Zugaldia @zugaldia.com · 09/05/2025
I don't know why I didn't try this before, from screenshot to calendar event in 5 seconds.
000
Antonio Zugaldia @zugaldia.com · 07/05/2025
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...
microsoft.com
Empowering multi-agent apps with the open Agent2Agent (A2A) protocol | The Microsoft Cloud Blog
Microsoft announces support for the open A2A protocol, helping to enable agent-to-agent interoperability across platforms. Learn more.
000
Antonio Zugaldia @zugaldia.com · 07/05/2025
"The previous iteration (03-25) now points to the most recent version (05-06), so no action is required to use the improved model" In other words, Preview version numbers mean nothing. developers.googleblog.com/en/gemini-2-...
developers.googleblog.com
Gemini 2.5 Pro Preview: even better coding performance- Google Developers Blog
Explore the new Gemini 2.5 Pro I/O Edition, featuring enhanced coding performance, video to code capabilities, and improvements for front-end web development.
000
Antonio Zugaldia @zugaldia.com · 06/05/2025
"You learn how to program. You learn how to fix things. But the hardest thing you’ll ever learn is when to leave them broken." This is the read I didn't know I needed today: notashelf.dev/posts/curse-...
notashelf.dev
The Curse of Knowing How, or; Fixing Everything | BlogGitHubTwitterRSS FeedGit Branch
A reflection on control, burnout, and the strange weight of technical fluency.
000
Antonio Zugaldia @zugaldia.com · 05/05/2025
Washingtonians, I can't recommend his YouTube channel enough. He provides unadulterated behind the scenes footage about the city's main events. And the occasional local food recommendations :⁠-⁠) youtube.com/@penguinsix?...
youtube.com
penguinsix
I'm a freelance photographer for the Washington D.C. media who makes up for the time when I'm not taking pictures by making videos of my life and life in the Nation's Capitol. An American who lived in...
020
Reposted by Antonio Zugaldia
e.w. niedermeyer @niedermeyer.online · 04/05/2025
a whole lot of people have no idea what a luxury it is to simply Walk To The Store
1355794827
Antonio Zugaldia @zugaldia.com · 02/05/2025
Remote MCP servers are a natural next step, what is unclear to me is how these services can monetize the investment.
000
Antonio Zugaldia @zugaldia.com · 30/04/2025
MCP server idea: Every GTK/GNOME app defines Actions that are available via D-Bus (e.g. screenshot below from GNOME Maps). The MCP server would bridge tool calls with D-Bus calls to any app in the desktop (whether it was designed to be controlled by LLMs or not!).
000
Antonio Zugaldia @zugaldia.com · 28/04/2025
If an image is ~258 tokens, and a token is ~0.75 words, then an image is worth 193.5 words. We've been lied to all our lives.
000