X / Twitter
F5-TTS released yesterday. Ported to MLX by @lllucas today.
Run it fast locally on a Mac:
https://t.co/wWduGRj7vG https://t.co/8XVOHKTXiR
Elevenlabs-level TTS on your laptop.
I'm always skeptical about new AI models hyped up sounding too good to be true. But this...is crazy good.
And now, you can run the gradio app by @realmrfakename on your laptop with 1 click.
Meet @elonmusk, from Silicon Valley.
Huggingface published an evaluation guidebook https://t.co/ewlxan8VlI
If you want to build an async-first multi-agent system, check out this fantastic tutorial by @jamescalam on @llama_index workflows!
Build a full research agent system by passing messages between an LLM reasoning module + web/RAG tools. The nice part about our workflows is you can write literally whatever you want in the steps, but take advantage of our async, event-driven orchestration.
Video: https://t.co/0i9avz3daY
Notebook: https://t.co/MSOmhxwWtK
To learn more check out our workflows guide: https://t.co/tNolgSm48v
introducing swarm: an experimental framework for building, orchestrating, and deploying multi-agent systems. 🐝
https://t.co/97n4fehmtM
https://t.co/sooTTdQIxD
A new blog post! I've realized that the idea of applying matrices to RGBA color vectors is not as well-known as I've thought, so I've wrote a comprehensive list of operations that can be represented this way, together with some motivation for doing so:
https://t.co/Jeq0TdAfCl
Podcastfy ai
Podcastfy is an open-source Python package that transforms web content, PDFs, and text into engaging, multi-lingual audio conversations using GenAI.
Unlike UI-based tools focused primarily on note-taking or research synthesis (e.g. NotebookLM ❤️), Podcastfy focuses on the programmatic and bespoke generation of engaging, conversational transcripts and audio from a multitude of text sources therefore enabling customization and scale.
people want your toddlers and babies to be read books with no words. it’s insane.
DocETL is our agentic system for LLM-powered data processing pipelines. Time for this week’s technical deep dive on _gleaning_, our automated technique to improve accuracy by iteratively refining outputs 🧠🔍 (using LLM-as-judge!) https://t.co/yVotz92SwL
MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion
*ST3R all the things! :)
https://t.co/f5ALDub45G
Very nice. Looks like it even displays the embedding space https://t.co/7Cg2G5bOuq
Introducing Lotus
A diffusion-based visual foundation model for dense geometry prediction. Achieves SoTA perf in two key geometry perception tasks: Zero-Shot Depth and Normal estimation. https://t.co/j3ednQOj1F
Dive into WebGPU—Part 1 (Tutorial)
by @martinlaxenaire
→ https://t.co/2zyRPnyPRH
In this 4-part series, you’ll learn to: ✨ Build 3D scenes with GPU-Curtains 💻 Sync DOM elements and interact with 3D objects 🎨 Create shading & particle systems using compute shaders. https://t.co/oSQclFR2Tb