speechrecognitionLibrary for performing speech recognition, with support for several engines and APIs, online and offline.
transformersTransformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
gttsgTTS (Google Text-to-Speech), a Python library and CLI tool to interface with Google Translate text-to-speech API
livekit-agentsA powerful framework for building realtime voice AI agents
inspect-aiFramework for large language model evaluations
fasttext-langdetect80x faster and 95% accurate language identification with Fasttext