Visualizing Cell Structures with Minecraft

Integrate LLM in any pipeline - fit/predict pattern, JSON driven flows, and built in concurency support.

Build datasets using natural language

A simple, hackable text-to-speech system in PyTorch and MLX

AI chat app built with Expo Router

Talk to any LLM with hands-free voice interaction, voice interruption, and Live2D taking face running locally across platforms

NeMo text processing for ASR and TTS

Reasoning Augmented Generation

This is an on-CPU real-time conversational system for two-way speech communication with AI models, utilizing a continuous streaming architecture for fluid conversations with immediate responses and…

React Native binding of whisper.cpp.

Controllable and fast Text-to-Speech for over 7000 languages!

Leverage the OpenAI Realtime API (12-17-2024) with this Next.js 15 starter template featuring shadcn/ui components, tool-calling & localization. Use starter to build Voice AI apps with WebRTC.

Free UI components I use for building Expo Router apps

Fully open reproduction of DeepSeek-R1

Simple text to phones converter for multiple languages

Speech-to-text, text-to-speech, speaker diarization, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC…

Dockerized FastAPI wrapper for Kokoro-82M text-to-speech model w/CPU ONNX and NVIDIA GPU PyTorch support, handling, and auto-stitching

LLM based autonomous agent that conducts deep local and web research on any topic and generates a long report with citations.

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

An open source real-time AI inference engine for seamless scaling

Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE)

Generate text and images using the CPU

Fast Multimodal LLM on Mobile Devices

A fast, local neural text to speech system

MLX Omni Server is a local inference server powered by Apple's MLX framework, specifically designed for Apple Silicon (M-series) chips. It implements OpenAI-compatible API endpoints, enabling seaml…

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.

Everything about the SmolLM2 and SmolVLM family of models