WebRTC pre-compiled library for android.

Python bindings of WebRTC Audio Processing

Open source SDK to the Fixie platform.

AudioBench: A Universal Benchmark for Audio Large Language Models

Some handy AI scripts

Simple Transformer in Jax

A fast multimodal LLM for real-time voice

https://www.shoufachen.com/Awesome-Diffusion-Transformers/

Green screen effect with HTML5 and JavaScript

📖 A curated list of resources dedicated to talking face.

Fast Diffusion Models with Transformers

Benchmarking suite for popular AI APIs

Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts, images, and 🔜 video, up to 5x faster than OpenAI CLIP and LLaVA 🖼️ & 🖋️

Unofficial Python API for character.ai

Lightweight GPT-4 Vision processing over the Webcam

State-of-the-art audio codec with 90x compression factor. Supports 44.1kHz, 24kHz, and 16kHz mono/stereo audio.

A WebGL Audio Visualizer

Talk to ChatGPT in real time using LiveKit

A playground where Otto can run free while hopefully not accidentally reformatting your hard drive

Plug in and Play Implementation of Tree of Thoughts: Deliberate Problem Solving with Large Language Models that Elevates Model Reasoning by atleast 70%

A guidance language for controlling large language models.

Examples and guides for using the OpenAI API

Collection of Summer 2025 tech internships!

Open-source pre-training implementation of Google's LaMDA in PyTorch. Adding RLHF similar to ChatGPT.

Fetch and archive the New York Times crossword leaderboard

Picture-in-Picture (PiP)