“Introducing Voice Design. Generate a unique voice from a text prompt alone. Is our library missing a voice you need? Prompt your own.
“NotebookLlama: An Open Source version of NotebookLM. @AIatMeta released an example of how to recreate @Google’s NotebookLM application using Llama and other open Models to convert PDFs into Audio Podcasts from pre-processing to text-to-speech. 👀 TL;DR: 🔄 Uses a multi-stage
Classic Christmas song gets authorized Spanish reworking thanks to ‘responsible’ AI | TechCrunch
GitHub – usefulsensors/moonshine: Fast and accurate automatic speech recognition (ASR) for edge devices
“Prepping for a 25-minute keynote: I exported a PDF of my slides to Gemini 1.5 Pro and dropped in an audio recording of my dry run. Gemini gave me precise feedback down to the slide and timestamp. After incorporating the suggestions, I recorded another round — total game changer.
Jacob Collier’s Lab Sessions: MusicFX DJ AI music tool
“It includes features like generating musical loops, transformation of sounds, and in-painting. Feedback through the Music AI Incubator has been essential to finding innovative and responsible ways to bring these technologies to people across the world. →” / X
HeyGen
“This is crazy, we’re so cooked. HeyGen 3.0 dropped new AI avatars that look real. The viseme morphing appears slightly slow, but 99% of people won’t notice its AI-generated content.
“This is wild! 🤯 An AI avatar joins a Zoom meeting and interacts like a real person. I don’t think the world understands where we are right now…
Suno
“Grammy-winning producer @Timbaland shares how Suno is helping him rediscover the purity of creativity in the debut episode of our new video series, MUSE. Hear more from Timbaland:
Leave a Reply