Gradio WebUI for creators and developers, featuring key TTS (Edge-TTS, kokoro) and zero-shot Voice Cloning (E2 & F5-TTS, CosyVoice), with Whisper audio processing, YouTube download, Demucs vocal isolation, and multilingual translation.
Notes 202631

by the bay © Juan B. Rodriguez
show in pixelfed.social
You might also like

Notes 202642
an open taxonomy of what children learn, migrating from nvm to mise, and a real-time speech-to-speech model with persona control

Notes 202641
a personal AI agent in your own Cloudflare account, a suite of open-source creative apps, an ultra-legible typeface, sideloading your own apps onto an iPhone, git worktrees and the Apple Siri Remote on Linux

Notes 202640
some new fonts, a self-hosted gym tracker, Lightroom reimplemented in Rust and an open-source Grok bot

Notes 202635
tolkien memorabilia, a time server & ai tooling

Notes 202629
token savings & ai tools

Notes 202625
play pacman, but as the ghost :)