Download
AudioEnhancerMAX is an open-source, local-first audio processing suite for podcasters, creators, and audio professionals. It combines enhancement, mastering, transcription, TTS, monitoring, and trusted-LAN edge workers in one FastAPI app.
The core pipeline runs on your machine: uploads, DSP processing, Whisper transcription, local Ollama/Gemma smart mode, Kokoro TTS, timing history, and reports stay under user control when local dependencies are installed. Optional Edge Neural TTS and Android worker offload are explicit and documented.
Features include noise reduction, wind/buzz/static/reverb cleanup, filler word detection, breath and mouth sound reduction, studio sound, Auto EQ, LUFS normalization, Demucs music preservation, streaming transcription, adaptive ETA, Apple Silicon monitoring, and smartphone worker pairing.
The v3.6 roadmap adds non-destructive editing, AI-assisted review, governance reports, offline-first mode, and output profiles.
Features
- Local-first audio enhancement and mastering
- AI-assisted noise reduction and cleanup
- Wind, buzz, static, reverb, and echo reduction
- Filler word detection for English and Italian
- Breath and mouth sound reduction
- Studio sound chain with compression and EQ
- Auto EQ and LUFS loudness normalization
- Demucs-based music preservation
- Streaming Whisper transcription
- TXT, SRT, VTT, and JSON transcript export
- Local Ollama / Gemma smart mode
- Kokoro local TTS voices
- Optional Edge Neural TTS
- Real-time CPU, GPU, ANE, RAM, and thermal monitoring
- Adaptive ETA and processing timing history
- Android smartphone worker pairing over trusted LAN
- v3.6 roadmap: non-destructive editing and governance reports
- MIT licensed
Project Samples
Categories
Audio EditingLicense
MIT LicenseUser Reviews
-
I like it!