Parkiet is a 1.6B parameter Dutch text-to-speech model (TTS)

Collection of awesome LLM apps with AI Agents and RAG using OpenAI, Anthropic, Gemini and opensource models.

🚀 The fast, Pythonic way to build MCP servers and clients

Damn Vulnerable MCP Server

Zonos-v0.1 is a leading open-weight text-to-speech model trained on more than 200k hours of varied multilingual speech, delivering expressiveness and quality on par with—or even surpassing—top TTS …

Minimal keyword extraction with BERT

Fast and personalized local speech-to-text

Tensorflow-based wake word detection

SCUDA is a GPU over IP bridge allowing GPUs on remote machines to be attached to CPU-only machines.

OVOS System and Volume event support for Mac OS

A simple, but performant framework for mapping speech directly to categories and intents.

NVIDIA Linux open GPU kernel module source

An application for running LLMs locally on your device, with your documents, facilitating detailed citations in generated responses.

Ask HuggingChat with OpenVoiceOS

Talk to HuggingChat through OpenVoiceOS

Self-hosted AI coding assistant

[Unmaintained, see README] An ecosystem of Rust libraries for working with large language models

A WebGPU-accelerated ONNX inference run-time written 100% in Rust, ready for native and the web

Open Voice OS and/or HiveMind installer using Ansible with an intuitive and easy Text-based User Interface

Open Voice OS plugin for Google AIY Voice Kit V2

WikiChat is an improved RAG. It stops the hallucination of large language models by retrieving data from a corpus.

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

[NeurIPS'22] Squeezeformer: An Efficient Transformer for Automatic Speech Recognition