Make Python Talk, Make Python Listen

This PyCon US talk explores how to implement speech capabilities in Python applications using accessible third-party packages. Learn to create text-to-speech functionality with PyTTSx3 and gTTS packages that leverage your operating system's speech engine. Discover how to implement speech recognition using the offline Whisper package to convert audio files into text without requiring advanced machine learning knowledge. The presentation also covers using yt-dlp for downloading web video and audio files for transcription purposes, and demonstrates how these technologies are implemented on the PyVideo.org website. With simple configuration requirements, implement these sophisticated speech features in just a few lines of code, making them accessible even to Python beginners.