🔥 Turn entire websites into LLM-ready markdown or structured data. Scrape, crawl and extract with a single API.

Open Source framework for voice and multimodal conversational AI

Simple text to phones converter for multiple languages

A collection of learning resources for curious software engineers

Audio Plugins created using C++ and Juce Framework

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

Official Pytorch Implementation of "Diff-HierVC: Diffusion-based Hierarchical Voice Conversion with Robust Pitch Generation and Masked Prior for Zero-shot Speaker Adaptation"

Localized watermarking for AI-generated speech audios, with SOTA on robustness and very fast detector

On-device Speech Recognition for Apple Silicon

VITS-based Voice Conversion focused on simplicity, quality and performance.

Efficient Training of Audio Transformers with Patchout

AI-based Audio Watermarking Tool

Stochastic Restoration of Heavily Compressed Musical Audio using Generative Adversarial Networks in Pytorch

Some random notes about Windows Audio Processing Objects (APOs).

[TMLR 2024] Efficient Large Language Models: A Survey

AEC3 Extracted From WebRTC

StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models

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…

A WebUI to create song covers with any RVC v2 trained AI voice from YouTube videos or audio files.

This Repository surveys the paper focusing on Prompting and Adapters for Speech Processing.

Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.

Audio processing by using pytorch 1D convolution network

Generative models for conditional audio generation

Stable Diffusion with Core ML on Apple Silicon

A toolkit for any-to-any encoder-decoder voice conversion systems

Easily train a good VC model with voice data <= 10 mins!