Text in audio (TTS)

Micro-TTS — client application for text-to-speech generation based on API.

Features:
Modern minimalist interface (Windows, HTML UI via pywebview)
Support for 30 voices with gender selection
Choice of pronunciation style (tone prompt, custom input)
Generation of up to 20 audio fragments (each block — separate wav)
Support for Russian, Ukrainian, English, 24 languages
Instant byte counter (limit control 5000/16000)
Flexible configuration via config.json file (API key, API model)
All voices and parameters — via separate voices.json
Secure storage of configs, easy transfer to another user

How it works:
Run the exe file, interface appears immediately (without console).
Enter text, select voice, set style if needed.
Generate audio (each block — separate file).
You can choose a folder for saving.

Result:
Ready audio files in the selected folder
High-quality voices

Technical implementation:
Python 3.10, PyWebView, API, support for building into exe (PyInstaller)
All UI — dynamic HTML, all settings via config
Screenshots of the interface, example of config structure, and full voices.json — attached.

#tts #python #voice #windows #ai #audiogeneration #pywebview