# TTS-Groq: Executive Overview
TTS-Groq is a cross-platform, modular, and extensible real-time speech-to-text (STT) application. It captures audio from the user's microphone, streams it to a pluggable transcription provider (such as Groq or OpenAI), and inserts the resulting text into the user's workflow or platform of choice.
## Core Value Proposition
- **Seamless Voice-to-Text:** Converts spoken audio to text in real time, enabling hands-free productivity.
- **Pluggable Providers:** Supports multiple STT providers, allowing flexibility and future expansion.
- **Platform Abstraction:** Designed for portability and easy adaptation to different operating systems.
- **Extensible Architecture:** Built with modularity and testability in mind, making it easy to add new features or providers.
## Key Features
- Real-time audio capture and chunking
- Asynchronous, non-blocking processing pipeline
- Hotkey-based and always-on modes
- Graceful shutdown and robust error handling
- Configurable via command-line and config files
## Typical Use Case
A user launches TTS-Groq, selects their preferred STT provider, and speaks into their microphone. The app transcribes their speech and inserts the text into their current application or workflow, triggered automatically or via hotkey.
---
For technical details, see [architecture.md](architecture.md) and [modules.md](modules.md).