AudioEnhancerMAX
fabriziodegni.com
- Free plan
- Open source
- Windows
- macOS
- Linux
What AudioEnhancerMAX is
AudioEnhancerMAX is an open-source audio suite for cleaning, transcribing, and mastering recordings, with processing designed to run locally. Its cleanup tools address noise, wind, buzz, static, reverb, breath, and mouth clicks; enhancement options also include Auto EQ, LUFS normalization, super-resolution, and Demucs music preservation. The Precision Speech Editor ties transcript text to suggested edits and renders only changes a user approves. Local Faster-Whisper transcription exports TXT, SRT, VTT, and JSON. The suite also lists text-to-speech, monitoring, edge processing, five delivery profiles, and WAV, MP3, and FLAC overrides. Optional integrations include local Ollama assistance, Microsoft Edge Neural TTS, and Android workers on a trusted LAN. The maker says core DSP and packaged transcription operate locally, while selected Edge TTS sends text to Microsoft and Android workers receive audio chunks over the LAN. The MIT-licensed software comes as a packaged app for Apple Silicon Macs (macOS 13 or later), and Linux and Windows run its core from source. Smart Enhance does not guarantee perfect restoration of damaged audio. The documented server binds to 127.0.0.1 by default; the maker advises additional safeguards before public exposure.
Who it suits
It may suit creators, podcasters, researchers, interviewers, and others with audio-heavy workflows who want local enhancement and transcription tools. Users considering public server access should account for the maker’s recommended safeguards.
Good to know, and what to watch
- Cleanup tools cover noise, wind, reverb, and mouth clicks
- Transcription exports TXT, SRT, VTT, and JSON
- Editor applies only approved transcript-linked changes
- MIT-licensed with a free plan
- Smart Enhance may not restore damaged audio perfectly
- Public exposure requires added server safeguards
- Selected integrations send text or audio over networks
The verdict
AudioEnhancerMAX combines audio cleanup, transcription, and mastering with a local-first approach to core processing. Its limits around damaged recordings and public server exposure matter when choosing how to use it.
What the maker publishes
- Audio cleanup
- Its listed cleanup features include noise, wind, buzz, static, reverb, breath, and mouth-click removal. source
- Audio cleanup
- Its listed cleanup features include noise reduction, wind, buzz, static, reverb and echo, breath, mouth-click, and silence handling. source
- Audio delivery
- The product lists five delivery profiles and validated WAV, MP3, and FLAC overrides. source
- Deployment limit
- The README advises against exposing the FastAPI server directly to the public internet without authentication, rate limiting, storage quotas, and a reverse proxy policy. source
- Enhancement
- Listed enhancement features include a studio sound chain, Auto EQ, LUFS normalization, super-resolution, and Demucs music preservation. source
- External data flows
- When selected, Edge Neural TTS sends text to Microsoft Edge TTS, and Android workers receive audio chunks over a trusted LAN. source
- Integrations
- Optional integrations include local Ollama assistance, Microsoft Edge Neural TTS, and Android workers on a trusted LAN. source
- Integrations
- Optional tools and components listed include local Ollama/Gemma, Kokoro voices, Microsoft Edge Neural TTS, and Android edge workers. source
- Intended users
- The maker describes the suite as built for creators, podcasters, researchers, interviewers, and audio-heavy workflows. source
- Intended users
- The project describes itself as built for creators, podcasters, researchers, interviewers, and audio-heavy workflows where privacy, control, and auditability matter. source
- License
- AudioEnhancerMAX is released under the MIT License. source
- License
- AudioEnhancerMAX is released under the MIT License. source
- Limit
- The maker says Smart Enhance is assistive analysis and does not guarantee perfect reconstruction of damaged audio. source
- Mac distribution
- The direct download, version 3.8.3 (build 3.8.4), is for Apple Silicon Macs running macOS 13 or later and is Developer ID signed, Apple notarized and stapled. source
- Platforms
- The README documents a packaged app for Apple Silicon Macs (macOS 13 or later), core local processing run from source on Linux and Windows, a browser interface served by the user's own local server, and an optional Android worker app for processing on a trusted LAN. source
- Privacy
- The maker says core DSP and packaged transcription run locally; optional external TTS and LAN processing are independently controlled. source
- Privacy
- The project says uploads, DSP output, timing history, and local model inference stay on the host unless an integration that sends data elsewhere is enabled. Transcription models may download on first use; after that, inference runs locally. source
- Product
- AudioEnhancerMAX is an open-source, local-first audio production suite for audio enhancement, transcription, and mastering. source
- Purpose
- AudioEnhancerMAX processes raw recordings into production-ready audio and includes enhancement, transcription, text-to-speech, monitoring, and edge processing. source
- Security
- The documented server binds to 127.0.0.1 by default, and the maker advises adding authentication, rate limiting, storage quotas, and a reverse proxy before public exposure. source
- Security
- The README says the server is documented for 127.0.0.1 by default, CORS is restricted to local origins, and user-controlled file IDs, download formats, versions, and preset IDs are validated. source
- Speech editing
- The Precision Speech Editor links transcripts to proposed edits, and only renders changes the user approves. source
- Speech editing
- It offers Whisper-based filler-word, hesitation, and stutter cleanup with natural crossfades. source
- Supported systems
- The packaged app is for Apple Silicon Macs on macOS 13 or later; on Linux and Windows, the maker's README supports core local processing run from source. source
Checked against the maker's pages on 4 Oct 2026.