EchoScribe

A modern web application for AI-powered audio and video transcription with comprehensive speech analytics.

Live Link

🔗 EchoScribe

Features

Core Transcription

• AI-powered transcription using Google Gemini 1.5 Pro
• 20MB file support for most audio/video formats
• High accuracy speech-to-text with automatic punctuation
• 15+ media formats including MP4, MP3, WAV, AVI, MKV

Smart Processing

• Automatic format conversion from video to audio
• Client-side media processing using FFmpeg.wasm
• URL/Google Drive integration for remote files
• Format optimization for better accuracy

Speech Analytics

• Filler word analysis identifying "um", "uh", and verbal pauses
• Speaking pace measurement in words per minute
• Speech clarity scoring and confidence assessment
• Engagement metrics and pace consistency tracking
• Interactive analytics dashboard with real-time charts

User Interface

• Modern, responsive design inspired by Medium.com
• Drag & drop file upload with visual feedback
• Real-time transcript editing with save functionality
• Multiple export formats including TXT and full analysis reports
• Clean filler word removal toggle

Tech Stack

Frontend

• Next.js 14 - React-based full-stack framework
• React 18 - Component-based user interface
• TypeScript - Type-safe JavaScript development

AI & Processing

• Google Gemini API - Advanced language model for transcription
• FFmpeg.wasm - Client-side media processing
• WebAssembly - High-performance audio/video manipulation