VoiceScribe is an AI-powered audio transcription application that converts speech from audio files into accurate and readable text. The application supports both Desktop and Android platforms using a single cross-platform architecture.

Built with Flutter and Python, VoiceScribe provides fast, reliable, and easy-to-use speech-to-text transcription for students, teachers, journalists, churches, businesses, content creators, and professionals.

• AI-powered speech-to-text transcription
• Supports multiple audio formats
• Export transcription as TXT files
• Cross-platform support:
  • Android
  • Windows
  • Linux
  • macOS
• Fast and accurate transcription engine
• Clean and modern UI
• Offline transcription support
• Multi-language capability
• Easy audio upload system

• MP3
• WAV
• M4A
• AAC
• FLAC
• OGG

• Flutter

• Python
• FastAPI
• Faster-Whisper

• OpenAI Whisper Model

project/
│
├── speech_backend/
│   ├── main.py
│   └── uploads/
│
└── speech_transcriber/
    ├── lib/
    ├── android/
    ├── windows/
    ├── linux/
    ├── macos/
    └── pubspec.yaml


# Author

Developed by Kelechi Obi

## Company

KeleTech AI

Building intelligent software solutions powered by AI and modern technologies.



@Powered by Keletech AI