AI Agent Skills

On-device Speech-to-Intent engine powered by deep learning

Real-time voice assistant — WebRTC streaming, faster-whisper ASR, local LLM, Vui Nano (300M) TTS. OpenAI Realtime API compatible. Voice cloning, barge-in, ~9× realtime o…

🐸STT - The deep learning toolkit for Speech-to-Text. Training and deploying STT models has never been so easy.

MARY TTS -- an open-source, multilingual text-to-speech synthesis system written in pure java

AI-powered multi-voice audiobook generator — LLM script annotation, voice cloning, voice design, LoRA training, per-line style control, and export to MP3, chaptered M4B,…

A modular Swift SDK for audio processing with MLX on Apple Silicon

Rapida is an open-source, end-to-end voice AI orchestration platform for building real-time conversational voice agents with audio streaming, STT, TTS, VAD, multi-channe…

On-device streaming speech-to-text engine powered by deep learning

Golang framework to build an AI that can understand and speak back to you, and everything else you want

📚 A customizable dictionary extension that supports double-click lookups in 20+ languages, 1000+ dictionaries, text-to-speech, translation and Anki integration.

pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label…

Speech Recognition for React Native Expo projects

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

DeepMind's Tacotron-2 Tensorflow implementation

WaveRNN Vocoder + TTS

🎙Speech recognition using the tensorflow deep learning framework, sequence-to-sequence neural networks