Easily migrate your codebase from one framework or language to another.

Official repo for consistency models.

YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open

The official Python API for ElevenLabs Text to Speech.

Text-to-Audio/Music Generation

Versatile audio super resolution (any -> 48kHz) with AudioSR.

A family of diffusion models for text-to-audio generation.

[ICLR 2025] SOTA discrete acoustic codec models with 40/75 tokens per second for audio language modeling

Multi-Scale Neural Audio Codec (SNAC) compresses audio into discrete codes at a low bitrate

unofficial vits2-TTS implementation in pytorch

YuE: Open Full-song Generation Foundation for the GPU Poor

Automated Drum Transcription Library

unofficial implementation of the High Fidelity Neural Audio Compression

Video+code lecture on building nanoGPT from scratch

fine-tuning MusicGen without prompts to generate music with a specific style