Speechfire door Jejkobb & sasoder

Speechfire transforms your browser into a powerful offline speech-to-text tool, allowing you to dictate text into any field without relying on cloud services. Built on OpenAI's Whisper model running locally through a Python backend, it provides accurate transcription while keeping your voice data on your own computer. Supports multiple languages and works with any text input field.

YOU NEED TO INSTALL THE SERVER AS WELL: https://github.com/Jejkobb/Speechfire

Key Features:
• Local Processing: Uses Whisper AI model running entirely on your machine
• Multiple Languages: Transcribe in various languages with high accuracy
• Universal Input: Compatible with any text field in Firefox
• Quick Access: Toggle recording with Alt+A hotkey
• System Integration: Easy server control through system tray
• Cross-Platform: Supports Windows and Linux systems

Works completely offline with no internet connection needed. The extension shows clear visual feedback through icon states to indicate recording status.

Technical Details:
- Backend: OpenAI Whisper model for speech recognition
- Local Server: Python-based for processing audio
- System Requirements: Python environment and basic system dependencies
- Browser Support: Firefox (Chrome version also available)
- OS support: Linux and Windows

An open-source tool that keeps your voice data local while providing reliable speech-to-text conversion.