The python library for real-time communication

koding with any LLMs

This is a cleanroom deobfuscation of the official Claude Code npm package.

TTS Towards Human-Sounding Speech

Taming Stable Diffusion for Lip Sync!

🚀 WebRTC - P2P - Simple, Secure, Fast Real-Time Video Conferences Up to 8k and 60fps, compatible with all browsers and platforms.

OpenAI-compatible TTS API for the GlaDOS TTS model

FULL v0, Cursor, Manus, Same.dev & Lovable System Prompts & AI Models.

A Conversational Speech Generation Model

A bidirectional pipeline parallelism algorithm for computation-communication overlap in V3/R1 training.

DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling

Prepare for DeekSeek R1 inference: Benchmark CPU, DRAM, SSD, iGPU, GPU, ... with efficient code.

ONNX implementation of Whisper. PyTorch free.

Real-time conversational AI on ESP32-S3 using LiveKit, WebRTC and SenseCap Watcher

A Toolkit to Help Optimize Onnx Model

This script allows to bypass Oracle Cloud Infrastructure 'Out of host capacity' error immediately when additional OCI capacity will appear in your Home Region / Availability domain.

A fast multimodal LLM for real-time voice

⚡ TabPFN: Foundation Model for Tabular Data ⚡

top-like script for rockhip NPUs on linux

YoloV8 NPU for the RK3566/68/88 with SAHI slicing

ONNXMLTools enables conversion of models to ONNX

An extremely fast Python package and project manager, written in Rust.

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

A terminal assistant for the hopelessly confused

ONNX Runtime Plugin for Unity

An espeak-compatible, permissively-licensed IPA phonemizer (G2P) based on DeepPhonemizer. Usable as a drop-in replacement for espeak's GPL phonemizer.

Babylon.cpp is a C and C++ library for grapheme to phoneme conversion and text to speech synthesis. For phonemization a ONNX runtime port of the DeepPhonemizer model is used. For speech synthesis V…

A collection of plain text dialogue datasets

g2p: English Grapheme To Phoneme Conversion