Clone a voice in 5 seconds to generate arbitrary speech in real-time

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

Open-Sora: Democratizing Efficient Video Production for All

SOTA Open Source TTS

Open-Source Frontier Voice AI

SoTA open-source TTS

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

A TTS model capable of generating ultra-realistic dialogue in one pass.

Lets make video diffusion practical!

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

End-to-End Speech Processing Toolkit

Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audi…

State-of-the-art TTS model under 25MB 😻

VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

Sharp Monocular View Synthesis in Less Than a Second

Event-driven networking engine written in Python.

Fully automatic censorship removal for language models

The most powerful local music generation model that outperforms most commercial alternatives

Speech To Speech: an effort for an open-sourced and modular GPT4-o

😝 TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, French, Korean, Chinese, German and Easy to adapt for other languages)

Noise supression using deep filtering

Implementation of MusicLM, Google's new SOTA model for music generation using attention networks, in Pytorch

A Flow-based Generative Network for Speech Synthesis

A sketch extractor for anime/illustration.

YouTube Full Text Search - Search all of YouTube from the command line

Kakao Hangul Analyzer III

The official implementation of HierSpeech++

SincNet is a neural architecture for efficiently processing raw audio samples.