The AT Protocol (🦋 Bluesky) SDK for Python 🐍

A Swift Wrapper for llama.cpp

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.

Speech-To-Text forced-alignment Speech processing Universal PERformance Benchmark

Three Ways of Using Large Language Models to Evaluate Chat. A system description of Dstc11 Track 4 submission.

A high-throughput and memory-efficient inference and serving engine for LLMs

Unified framework for building enterprise RAG pipelines with small, specialized models

Simple WebSocket server and client for Python.

Password protect a static HTML page, decrypted in-browser in JS with no dependency. No server logic needed.

Create an LJSpeech structured voice dataset on wave input

The definitive Web UI for local AI, with powerful features and easy setup.

Official repo for “MooseNet: A Trainable Metric for Synthesized Speech with a PLDA Module”

Ecoute is a live transcription tool that provides real-time transcripts for both the user's microphone input (You) and the user's speakers output (Speaker) in a textbox.

feature extraction from speech signals

🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.

An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

AudioLDM: Generate speech, sound effects, music and beyond, with text.

An async Python micro framework for building web applications.

Network Analysis in Python

p5.sound brings the Processing approach to Web Audio and p5.js. Demos:

Extensible memoizing collections and decorators

A Python DB-API 2.0 client for the AWS Aurora Serverless Data API

Real-time video and audio processing on Streamlit

Real time video and audio processing examples with Streamlit and streamlit-webrtc

An AWS Aurora Serverless Data API dialect for SQLAlchemy

General Speech Restoration

[Legacy] Data & AI Notebook templates catalog organized by tools, following the IMO (input, model, output) framework for easy usage and discovery..

Wrapper to use boto3 resources with the aiobotocore async backend

🐚 Python-powered shell. Full-featured and cross-platform.

PyTorch implementation of GAN-based text-to-speech synthesis and voice conversion (VC)