What I Built
MixMaster AI is an AI-powered audio mastering system. You upload a raw audio file, describe what you want in plain English, and Claude handles the entire mastering chain automatically.
GitHub: https://github.com/Tanzil-Ahmed/mixmaster-ai
The Problem
Audio mastering requires deep technical knowledge — EQ curves, compression ratios, loudness targets, stereo imaging. Most musicians and indie creators can't afford a mastering engineer for every track.
I built one with Claude.
How It Works
1. Audio Analysis
Claude analyzes 13 acoustic measurements from the uploaded file — loudness (LUFS), dynamic range, crest factor, spectral balance, stereo width, true peak, and more using librosa and pyloudnorm.
2. AI Decision Making (Claude tool_use)
Claude reads the measurements + your creative brief and sets every DSP parameter — EQ frequencies and gains, compression ratio and threshold, saturation amount, stereo width, limiter ceiling.
3. Signal Processing Chain
The full mastering chain runs using Spotify's pedalboard library:
- Corrective EQ (high-pass, surgical cuts)
- Compression (ratio, threshold, attack, release)
- Saturation (harmonic enhancement)
- Stereo imaging (mid-side processing)
- Limiting (true peak control, TPDF dither)
4. Output
Streaming-ready WAV at -14 LUFS with true peak control. Professional quality, zero manual knob-turning.
Tech Stack
- Python
- Anthropic Claude API (tool_use)
- Spotify pedalboard (DSP chain)
- librosa + pyloudnorm (audio analysis)
- FastAPI (REST endpoint)
- Gradio (UI)
Three Interfaces
The same mastering engine is exposed three ways:
- Gradio UI (drag and drop)
- REST API (/master endpoint)
- CLI (command line)
What's Next
- Stem mastering (separate vocal, drums, instruments)
- Genre-aware presets
- Batch processing
Star the repo if you find it useful.
Top comments (0)