Metadata-Version: 2.4
Name: hitech-stt-jarvis
Version: 0.2.0
Summary: An ultra-accurate, cloud-powered Speech-to-Text library using Selenium WebDriver.
Author: Priyanshu Pal
License-File: LICENSE
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Requires-Python: >=3.10
Requires-Dist: selenium>=4.0.0
Requires-Dist: webdriver-manager>=4.0.0
Description-Content-Type: text/markdown

# HiTech-STT-Jarvis

An ultra-accurate, continuous speech-to-text listener engine powered by automated cloud web-speech streams, optimized for voice assistants like JARVIS.

## Features
- **Cloud-Grade Accuracy:** Leverages web-stream speech recognition for flawless parsing, context detection, and automatic punctuation.
- **Zero Local Footprint:** No heavy acoustic model files to download or update locally.
- **Background Multithreading:** Runs silently inside an automated, headless browser thread.
- **State Management Native Integration:** Seamlessly shifts between `IDLE`, `PROCESSING`, and `ACTIVE` assistant states.
- **Smart Audio Barge-In:** Tracks real-time voice intervals to instantly signal audio playback interruption requests.

## Installation
```bash
pip install hitech-stt-jarvis