A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

PersonaPlex code.

MOSS-Audio-Tokenizer is a Causal Transformer-based audio tokenizer built on the CAT architecture. Trained on 3M hours of diverse audio, it supports streaming and variable bitrates, delivering SOTA …

Silero VAD: pre-trained enterprise-grade Voice Activity Detector

A powerful framework for building realtime voice AI agents 🤖🎙️📹

Build resilient language agents as graphs.

End-to-end realtime stack for connecting humans and AI

LiveKit real-time and server SDKs for Python

Lightning-Fast, On-Device, Multilingual TTS — running natively via ONNX.

Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Andr…

Fine-tuning Moshi/J-Moshi on your own spoken dialogue data

10 Lessons to Get Started Building AI Agents

Optimized OpenAI's Whisper TFLite Port for Efficient Offline Inference on Edge Devices

Robust Speech Recognition via Large-Scale Weak Supervision

A torch implementation of a recursion which turns out to be useful for RNN-T.

A fast parallel implementation of RNN Transducer.

Faster Recurrent Neural Network Language Modeling Toolkit with Noise Contrastive Estimation and Hierarchical Softmax