Catchy melodies made with a diffusion-based neural net assistant
I've created a diffusion-based neural net generative assistant that makes creating new melodies much easier, even for non-musicians like me. These are meant to be just the catchy "hook" parts of songs, so more work is required to make them into full songs, but this is already handled well by existing products (e.g. there are plugins that can suggest a few possible chord progressions based on the melody and there is even good singing software that I used without any tweaks to make the “voice” playlist: Synthesizer V Studio). This side project turned out to be quite challenging because of how…
In plain words
This tool uses a diffusion-based neural network to generate catchy melodic hooks for songwriting, making melody creation accessible to non-musicians. The assistant produces short, hook-focused melodies that users can develop into full songs using existing tools for chord progression and vocal synthesis. The creator trained the model on limited melodic data, employing advanced generalization and augmentation techniques to overcome data scarcity challenges typical of specialized music AI applications.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
I've created a diffusion-based neural net generative assistant that makes creating new melodies much easier, even for non-musicians like me. These are meant to be just the catchy "hook" parts of songs, so more work is required to make them into full songs, but this is already handled well by existing products (e.g. there are plugins that can suggest a few possible chord progressions based on the melody and there is even good singing software that I used without any tweaks to make the “voice” playlist: Synthesizer V Studio). This side project turned out to be quite challenging because of how little data there is to train on - several orders of magnitude less than DALL-E or GPT-3 had available for its training, so it required a deep dive into research of new generalization and augmentation techniques and some feature engineering. Various other instruments: Voice: https://www.youtube.com/playlist?list=PLoCzMRqh5SkE1yC8_WtJ-... Synth: https://www.youtube.com/playlist?list=PLoCzMRqh5SkFj7RNZvjr7... Bell: https://www.youtube.com/playlist?list=PLoCzMRqh5SkEYHYvHX9m9... Guitar: https://www.youtube.com/playlist?list=PLoCzMRqh5SkGKvfkP2Oex... Sax: https://www.youtube.com/playlist?list=PLoCzMRqh5SkHfsZgzzdSh... Grand Piano: https://www.youtube.com/playlist?list=PLoCzMRqh5SkFMch5x60uh... SoundCloud electric piano: https://soundcloud.com/lech-mazur-995769534/sets/ai-assistan... SoundCloud vocal: https://soundcloud.com/lech-mazur-995769534/sets/ai-assistan...
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, May 2022
the whole month →
Peerlist▲1,052A professional network w/ robust work profiles at its core
Life & fun · 2022 · peerlist.io
- MA
Life & fun · 2022 · github.com
