Download
AudioEnhancerMAX is the open-source AI-powered audio media center for podcasters, creators, and professionals. It runs 100% locally on your hardware — no cloud, no subscriptions, no limits.
Features: 16+ intelligent audio filters (AI noise removal, filler word detection, breath reduction, studio sound, audio super-resolution), Gemma 4 AI dynamic parameter tuning, distributed edge computing across Android smartphones, real-time system monitoring for Apple Silicon.
Built with FastAPI, Whisper Large-v3, Pedalboard (Spotify), noisereduce, DeepFilterNet, and Gemma 4 via Ollama. Optimized for Apple Silicon M3 MAX.
Unlike Adobe Podcast ($9.99/mo), Descript ($24/mo), or iZotope RX ($1,349), AudioEnhancerMAX is free forever and keeps your audio private. MIT Licensed.
AI noise removal with wet/dry mixing
Filler word removal (English + Italian)
Breath and mouth sound reduction
Studio sound with broadcast compression
Gemma 4 AI dynamic parameter tuning
Distributed edge computing (
Features
- AI noise removal with wet/dry mixing Filler word removal (English + Italian) Breath and mouth sound reduction Studio sound with broadcast compression Gemma 4 AI dynamic parameter tuning Distributed edge computing (Android workers) Audio super-resolution up to 96kHz Real-time CPU/GPU/ANE system monitor AI transcription (Whisper, 99+ languages) Smart Mode with auto content classification 100% local processing, zero cloud
Project Samples
License
MIT LicenseUser Reviews
-
I like it!
