It seems very odd that so many complex LLM features like image generation
are available and run locally but I can't find one that will do text-to-speech.<p>I need local because the end-user does not have regular web connectivity.<p>The idea case is reading PDFs during plane flights.<p>Even Dragon Systems (anyone remember "Barnburner One..."?) now is cloud connected.
OpenAI Whisper model is open source and can be run locally. There is a "light" version also to help it run on lower resourced machines, e.g local machine perhaps
Check out Piper TTS: <a href="https://github.com/rhasspy/piper">https://github.com/rhasspy/piper</a><p>Note: I tried to run it on MacOS and had an issue with Python compatibility - ended up running it in a Docker container, got it working fine. If you experience the same issue, let me know - happy to share the code.