Skip to content

Category

Audio & Voice

Speech synthesis, music generation, and everything the open ecosystem can make you hear.

3 verified projects

AudioOpen · MIT

Chatterbox

ElevenLabs-tier speech, MIT-licensed

★ 24.5kmaintained

AudioOpen · Apache-2.0

HeartMuLa

The Stable Diffusion moment for music

★ 3.8kmaintained

AudioOpen · Apache-2.0

Kokoro

82 million parameters that sound like a thousand times more

★ 7k+; among HF's most-downloaded TTSstable

Keep exploring

Agents & Coding Models & Weights Local & Private AI Generative Media Retrieval & Knowledge Computer Vision Robotics & Embodied AI Science & Data Experimental & Unusual