🎙️ Modern Voice Tweaker Web App

A professional-grade, browser-based voice recording and processing studio with AI-powered creative tools.

🚀 Overview

Voice Tweaker Studio is a comprehensive web application for recording, editing, and enhancing voice recordings with advanced audio processing capabilities. Built entirely with client-side web technologies, it offers professional-grade voice recording, real-time audio effects, AI-powered content generation, and video integration - all without requiring server infrastructure.

✨ Key Features

🎤 Voice Recording & Processing

• Multi-take recording with punch & roll capabilities
• Real-time voice effects (pitch shift, reverb, compression, etc.)
• Voice preset system for quick character switching
• Advanced audio processing (noise reduction, normalization)

🤖 AI-Powered Creative Tools

• AI Script Writer - Generate custom scripts from prompts
• AI Story Generator - Create detailed stories with context
• AI Character Voice Analyzer - Extract character voice profiles
• AI Voice Preset Generator - Create voice presets from descriptions

🎬 Video & Subtitle Integration

• Video import and timeline synchronization
• Subtitle creation and editing with timestamps
• Multi-language translation with 20+ supported languages
• Translation memory system for consistent translations

🎛️ Professional Audio Workflow

• Multi-track mixer with volume, mute, solo controls
• Track reordering and length adjustment
• Background music looping for continuous ambiance
• Waveform visualization and editing

💾 Project Management

• Local storage for recordings and projects
• Export options for audio, video, and subtitles
• Folder organization system

🛠️ Technology Stack

• Framework: Next.js with React 18 (App Router)
• UI: Tailwind CSS with shadcn/ui components
• Audio Processing: Web Audio API
• Storage: IndexedDB and LocalStorage
• AI Integration: Google Gemini API
• Video Processing: HTML5 Video API
• State Management: React Context API and custom hooks

🚀 Getting Started

Prerequisites

• Modern web browser (Chrome, Firefox, Edge recommended)
• Google Gemini API key (for AI features)

Installation

1. Clone the repository: ```bash git clone https://github.com/yourusername/voice-tweaker-studio.git cd voice-tweaker-studio ```

2. Install dependencies: ```bash npm install ```

3. Create a .env.local file with your API keys: ``` NEXT_PUBLIC_GEMINI_API_KEY=your_gemini_api_key_here ```

4. Start the development server: ```bash npm run dev ```

5. Open http://localhost:3000 in your browser.

📖 Usage Examples

Basic Voice Recording

1. Click the "Record" button to start recording
2. Speak into your microphone
3. Click "Stop" when finished
4. Preview your recording with the "Play" button
5. Save or discard the recording

Using AI Script Writer

1. Navigate to the AI Script Writer panel
2. Enter a prompt (e.g., "A comedy scene between two friends at a coffee shop")
3. Click "Generate Script"
4. Review and edit the generated script
5. Click "Load to Transcript" to prepare for recording

Multi-Track Mixing

1. Record your voiceover or import existing audio
2. Add background music tracks
3. Adjust volumes, start times, and durations
4. Enable looping for background tracks if needed
5. Reorder tracks as necessary
6. Export the final mix

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgements

• Made with ❤️ by criptichood
• Built with Next.js and React
• UI components from shadcn/ui
• AI capabilities powered by Google Gemini