Hey all,
Almost as impressive as all the LLMs these days is the voice that ChatGPT uses with its emphasis and dramatic pauses and umms, etc.
I would love to integrate that with a self-hosted Llama3 engine.
Is there a project that y’all have heard of?
Librera FD as your reader app: https://www.f-droid.org/en/packages/com.foobnix.pro.pdf.reader/
Sherpa Onnx as your TTS engine: https://github.com/k2-fsa/sherpa-onnx
I recommend the piper TTS pretrained models, either Lessac medium or Kusal high/medium