Fidel Ecco

While building Lima & Chattier, I learned a ton about face landmark estimation from video and 3D face blendshapes for speech animation. Here are the tools and papers that helped me the most 🧵👇 #AI #ComputerVision #3DAnimation #GameDev #IndieDev #BuildInPublic

Spent years doing it wrong, overcomplicating features and delaying my launches for no reason. I have a strong gut feeling that @shipordie_ is the right way to break the loop. Ready to build fast and ship with the crew! 🏴‍☠️

@ekzhang1 Thanks man! This library rocks 🤟

I'm open-sourcing jax-js — a machine learning library for the web, in pure JavaScript jax-js is the first ML compiler that runs in the browser, generating fast WebGPU kernels. Built from scratch over the past year as a personal side project Details: ekzhang.substack.com/p/jax-js-an-ml…

@code_like_parge Valid point for Windows users! I actually didn't know about Win+H. My use case: 1. I run Ubuntu, so no native tools available. 2. LLMs. Dictating complex prompts is drastically faster than typing. In the AI era, speech-to-text is a huge productivity unlock.

@fidel_ecco lol, just press "Windows + H" on your windows machine. I'm pretty sure there would be some similar shortcut in Mac and Linux. But an app for "speech-to-text", why?

I’ve started using Handy to transcribe everything directly onto my screen and I might never go back to typing manually. The flow is incredible. handy.computer #BuildInPublic

📊 Building PlotPink - engineering data viz that doesn't take forever to set up. Shipping fast this time (shoutout to @marclou). Chasing the dream tool I’d actually want for my full-time engineering work. 🚀

Nvidia's Audio2Face-3D blows me away, but needs dedicated inference servers + Nvidia AI Enterprise license (ouch for solo builders) Meta's Oculus Lipsync is lightweight enough to run locally on anything, just basic visemes without expressions though Is there a middle ground?🤔

@StevenMusielski @joshkaufman @UriLevine1 @ericries Books give you the deep dive, X gives you the highlights reel. Both have their place, depends what you're optimizing for that day.

@fidel_ecco @joshkaufman @UriLevine1 @ericries Great books. Do you ever find you learn more from reading posts on X than reading books?

My recent favorites 📚 1️⃣ The Personal MBA - practical business insights. 2️⃣ Fall in Love with the Problem, Not the Solution - solve the right problems. 3️⃣ The Lean Startup - test ideas fast and smart. Loved these reads! @joshkaufman @UriLevine1 @ericries

@tomhaerter Thanks for the feedback! Recently tested OpenAI's realtime speech model. Amazing result, but wow, the cost! Gemini Live API can be a bit more budget-friendly.

That's a pretty cool idea I would focus on reducing the latency and making it more free-form, like they don't have to necessarily always press the mic button, so it's more like a phone call I think Elevenlabs on their landing page has slightly better latency. If you can wire that up with your avatars, that could be pretty nice

reply with your startup or product, and I will give you my humble opinion on how you can improve

My endless cycle of ambitious projects... Get sucked in for months trying to force these big ideas to work. Then realize I probably should've just shipped something simple instead. Sound familiar?

Why does Android’s on-device speech to text cut off after a few seconds of silence or even mid-speech, even though it’s running locally? Docs say it’s “likely to stream audio to remote servers… not intended for continuous recognition” but that is not the case here.

I run Chattier, a SaaS for multilingual AI chatbots. Now I’m turning that tech into an English speaking practice app. 🎙️ 10 hours in, aiming to launch in ~3 weeks. Excited to share the journey and updates along the way.

@10x_vibecoding Great! Much needed.. I'm in!

@fidel_ecco That why I created x.com/i/communities/…

Every Build in Public community on X: - Share your work! ✅ - No self-promotion! ❌ Can anyone explain how this works in practice? 😅

@mazeincoding Yep, it's quite rare to find actual value content in that community

this is the saddest thing that exists on this app. should be called "ask stupid questions in public", not "build in public"

🚀 Really struggling to pinpoint the right niche users for Chattier (my SaaS for 3D AI avatars + customer support). Where do you think I could find the people who’d benefit most?

@thekitze Folks at mythic.ai would agree

analog is going to make a HUGE comeback in the next 5 years you can already feel the tech fatigue

If you’re working on avatars, facial tracking or speech animation these tools are gold. Got more resources? Drop them below 👇 If you found this thread useful, share it so others can discover it too 🙌 #AI #GameDev #BuildInPublic

Audio-driven facial animation in MetaHuman Animator Converts audio to realistic facial animation, real-time or offline. Fully integrated in @UnrealEngine. 🔗metahuman.com 🔗dev.epicgames.com/documentation/…

While building Lima & Chattier, I learned a ton about face landmark estimation from video and 3D face blendshapes for speech animation. Here are the tools and papers that helped me the most 🧵👇 #AI #ComputerVision #3DAnimation #GameDev #IndieDev #BuildInPublic