docs/tts-module-spec.md

refer to test_modules/app_supertonic_tts_demo.py

• use supertonic tts library
• in this demo, input text is generated to speech data using supertonic.TTS
• text is firstly divided into multiple chunk text by statements and stored in buffer list
• and TTS generation is running for the list of text chunks
• this is to generate audio quickly for long text book.

TODO

• make tts.py and make module refering to app_supertonic_tts_demo.py
• In library menu, "Tap to play" button is clicked and the book text is chuncked and stored in buffer list.
• user click the play button and the text chunk list is converted to audio one by one.

package dependencies

Supertonic TTS

supertonic>=1.3.1 soundfile>=0.12.0 onnxruntime>=1.18.0 huggingface-hub>=0.23.0