Project Info
Inspiration
MixMate was inspired by our experience in live sound engineering. Spending hours mixing live performances, we often encountered recurring challenges: feedback, inaudible singers, harsh frequencies, and the pressure of keeping audiences engaged. Existing tools provided either raw visualisation or basic analysis, leaving a gap for actionable, intelligent guidance. MixMate was built to fill this gap, combining audio analysis with AI-driven insights and intermission music generation. What It Does MixMate empowers live audio engineers by providing: Real-Time Audio Analysis - Visualise and monitor every frequency band during live shows or with prerecorded tracks. Raw Mix Insights - Identify muddiness, harsh highs, and tonal imbalances, giving a clear overview of the mix. AI-Powered Recommendations - Claude analyses the audio and generates precise EQ, compression, and mix adjustment suggestions tailored to the venue and setup. Intermission Music Generation - Suno creates seamless, vibe-matched instrumental tracks inspired by the previous track, keeping audiences engaged between sets. How We Built It Audio Engine & Analysis: AVAudioEngine with FFT-based feature extraction to deliver live and offline audio analysis with minimal latency. AI Integration: Structured prompts for Claude and Suno to produce recommendations and musical intermission tracks. User Interface: Built in SwiftUI, the dashboard displays frequency spectra, detected issues, AI insights, and generated prompts intuitively. Accomplishments Developed a robust real-time audio analyser capable of functioning in live venues of all sizes, and across various music genres. Created a reliable Claude prompt system for actionable mix recommendations. Integrated Suno intermission music generation directly into the app workflow. Integrated Suno intermission music generation directly into the app workflow. Designed a unified dashboard that displays the Real-Time Analyser, AI insights, and generated music prompts in one place. What's Next! Expanding AI recommendations to support complex multi-instrument setups. Developing venue-adaptive recommendations, adjusting based on acoustics and audience size. Offering customisable intermission music styles, including genre, tempo, and mood options. Conducting more in-depth music analysis to confirm the key, genre, and tempo of each input. Launching cross-platform support for macOS, Android, and integration with live sound consoles (DiGiCo, Yamaha, Allen & Heath).
This repository has no readme, or GitHub could not be reached.
Analysis
View
Metric
No commits on this project resolved to a GitHub account.
Technology
- SwiftIn code
1 of 1 appear in the indexed code.
AI coding agents
No AI coding agent signals were found in this repository.
Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.
Codebase size
Source size
61 KB
Source files
19
Counts recognized source files only; vendored directories, binaries and lockfiles are excluded, so this is smaller than the repository on disk.
Repository
Rahuuuul/TreeHacks-26-Public
30 files · 5.2 MB · @ 8db76e0
Structure
Interface
7 files · 23%Screens, components and styles rendered to the user.
Application logic
20 files · 67%Domain rules, services and shared utilities.
Supporting
Layers are inferred from where files sit in the tree, not from reading the code. A project that names its directories unconventionally will read oddly here — open the file browser to check anything the diagram implies.
Languages
- Swift100%
Share of indexed source by file size. Binary and vendored files are excluded.
This project’s features have not been analysed yet.
Export this project's context (description, README, evidence, key source files) to chat with an AI agent elsewhere.