Skip to content

Valencier/VoiceEnhancer

Repository files navigation

VoiceEnhancer AI

License: MIT Stars Version 1.0.0


VoiceEnhancer AI is an advanced utility for adaptive microphone noise suppression, echo cancellation, and voice clarity boosting. It leverages AI-powered acoustic profiling for optimal results in any environment.


⚠️ Important: Acoustic Calibration Required

  • Source code runs in demo mode. For full noise suppression and all features, download the pre-calibrated release from Releases.
  • Demo mode: All controls visible, but Apply buttons are disabled. Acoustic profile file (acoustic_model.dat) is required for full version.
  • Pre-built releases include a pre-trained acoustic model and work out of the box.

Features

  • Noise Suppression: Adaptive AI filter removes background noise from your microphone input.
  • Echo Cancellation: Reduces echo and feedback for clearer communication.
  • Voice Clarity Boost: Enhances vocal presence and intelligibility.
  • Acoustic Profiling: Full version adapts to your room's acoustics for best results.
  • Modern GUI: Dark-themed, intuitive interface with progress bars and real-time feedback.
  • Logging: All operations are logged for troubleshooting.

System Requirements

  • Windows 10/11 (x64)
  • Microphone
  • Python 3.8+
  • For full version: pre-built release with acoustic_model.dat

Installation

Pre-built Release (Recommended)

  1. Download the latest release from GitHub Releases
  2. Unpack and run VoiceEnhancerAI.exe

From Source (Demo Mode)

  1. Clone the repository:
    git clone https://github.com/Valencier/VoiceEnhancer.git
    cd VoiceEnhancer
  2. Install dependencies:
    pip install -r requirements.txt
  3. Run the application:
    python src/main.py

Demo Mode

  • In demo mode, all sliders are active, but Apply buttons are disabled.
  • To unlock all features, download the pre-calibrated release.

FAQ

Q: Why demo mode?

A: Demo mode is provided to allow users to explore the interface and features. Full functionality requires an acoustic profile file (acoustic_model.dat) generated during model training on a build server. This ensures optimal noise suppression tailored to your environment.

Q: How to get the full version?

A: Download the pre-built release from the Releases page. It includes a pre-trained acoustic model.

Q: Is it safe?

A: Yes. The application is open-source and does not transmit audio data externally. All processing is local.


Troubleshooting

  • If you see "Acoustic profile not found. Running in demo mode.", ensure you are using the pre-built release.
  • For audio device errors, check your microphone connection and permissions.
  • For PyAudio issues, see PyAudio documentation.
  • Check voiceenhancer.log for detailed logs.

Contributing

Contributions are welcome! Please see CONTRIBUTING.md for guidelines.



License

This project is licensed under the MIT License. See LICENSE for details.


Project Structure

VoiceEnhancer/
├── .github/workflows/release.yml
├── src/
│   ├── __init__.py
│   ├── main.py
│   └── acoustic_check.py
├── README.md
├── LICENSE
├── requirements.txt
├── setup.py
└── .gitignore

Changelog

See Releases for version history.


Maintainer


Disclaimer

This software is provided as-is. Acoustic calibration is required for full functionality. Building from source produces demo version only.