[x] fix play audio output [ ] headless browser [ ] pyproject proper struct [ ] get rid of mozzilla tts and upgrade to python3.11 or atleast 3.10 [ ] get rid of bloated tts mozzila package that has 1B dependencies from the summer of '69 [ ] refactor into senses high abstraction layer into very basic agent for easy config [ ] dynamic config [ ] basic cli with flags [ ] basic gui with tk ... [ ] models in tinygrad
project struct
https://matt.sh/python-project-structure-2024
https://www.geoffreylitt.com/2023/03/25/llm-end-user-programming.html
clutter
https://www.youtube.com/watch?v=E2shqsYwxck
https://www.youtube.com/watch?v=jENqvjpkwmw
https://www.youtube.com/watch?v=GxLoMquHynY
https://www.youtube.com/watch?v=QxHE4af5BQE
https://www.youtube.com/watch?v=mdV8lETtGY4
https://www.youtube.com/watch?v=KVOWPeV9s00
https://www.youtube.com/watch?v=V1Mz8gMBDMo
https://www.youtube.com/watch?v=iIWbhwLyDQQ
https://www.youtube.com/watch?v=f1ihg20fQiU
https://www.youtube.com/watch?v=Oe-7dGDyzPM
https://www.youtube.com/watch?v=ztBJqzBU5kc
https://www.youtube.com/watch?v=piFuaOrpfN4
ideas: https://www.youtube.com/watch?v=7VAs22LC7WE
conversation -> ollama api
browser -> scrapegraphai
speech -> vits or openvoice
https://github.com/myshell-ai/OpenVoice/blob/main/docs/USAGE.md
https://github.com/myshell-ai/OpenVoice/blob/main/demo_part3.ipynb
https://huggingface.co/docs/transformers/en/model_doc/vits
listen -> wav2vec or whisper local
https://huggingface.co/docs/transformers/en/model_doc/whisper
https://huggingface.co/docs/transformers/en/model_doc/wav2vec2