Cloning a musical instrument from 16 seconds of audio
In 2020, Magenta released DDSP [1], a machine learning algorithm / python library which made it possible to generate good sounding instrument synthesizers from about 6-10 minutes of data. While working with DDSP for a project, we realised how it was actually quite hard to find 6-10 minute of clean recordings of monophonic instruments. In this project, we have combined the DDSP architecture with a domain adaptation technique from speech synthesis [2]. This domain adaptation technique works by pre-training our model on many different recordings from the Solos dataset [3] first and then…
Cloning a musical instrument from 16 seconds of audio launched on February 25, 2022 with 185 votes, #143 of 2,645 launches that month and more than 95% of that year's launches. The site was still online in September 2026, 4 years on.
In plain words
This tool creates playable instrument synthesizers from just 16 seconds of audio recording, using machine learning to clone the sound of monophonic instruments. It combines Google's DDSP algorithm with domain adaptation techniques, requiring far less training data than previous approaches that needed 6-10 minutes of recordings. The tool is designed for musicians and sound designers who want to generate custom instrument models quickly without extensive audio samples.
written from the facts on this page · September 2026
From the sources
A collaborative AI workspace, built on your company context. Build and orchestrate agents right alongside your team
JavaScript must be enabled in order to use Notion. Please enable JavaScript tofrom erlj.notion.site
In the maker’s words, at launch
In 2020, Magenta released DDSP [1], a machine learning algorithm / python library which made it possible to generate good sounding instrument synthesizers from about 6-10 minutes of data. While working with DDSP for a project, we realised how it was actually quite hard to find 6-10 minute of clean recordings of…
Does a similar job
all alternatives →
Stable Audio 2.02024 · stability.ai · ▲156One shot sample generation for the SignalsAndSorcery.com platform - shiehn/sas-sample-generator
AI Voice Cloning by Wavel2023 · wavel.ai · ▲360High-quality voice clones with just 60 seconds of audio
- FAFree AI-based music demixing in the browser2023 · sevag.xyz · ▲190
Hi all, I've spent some time working on music demixing or music source separation algorithms, which take in a mixed song and output estimates of isolated components (e.g. vocals, drums, bass, other). I took a popular PyTorch model with good performance (Open-Unmix, UMX-L weights), reimplemented the inference steps in C++, and compiled it to WebAssembly for a free client-side music demixer.
Building musical synthesizers with SQL queries2023 · github.com · ▲176If you already know what bytebeat is, you don't need an explanation. If not, check my project :) Here is how it looks: SELECT mono(output( arraySum(x -> 1 / 6 * running_envelope(30 * (1 + x / 6), time, 0.05 * x, 0.005, lfo(0, 0.25, sine_wave, time / 8), 0.1) * sine_wave(time * 80 * exp2(x / 3)), range(12)))) FROM table; To check how it sounds, find the examples in the repository https://github.com/ClickHouse/NoiSQL
- MAMusic Audio Search Engine Using OpenAI's Embeddings on GPT Descriptions2023 · muzic-sage.vercel.app · ▲92
I am excited to announce a new tool for music producers and audio enthusiasts - a music audio search engine. With just a simple description of the groove you're looking for, our semantic search engine will output the most similar audio in seconds. I used the Freesound.org API to upload over 3,000 grooves to MongoDB, and combined all the relevant data such as tags, title, description, BPM, etc. into OpenAI's Text-Davinci to generate a unique description of each sound. I then embedded these descriptions using the Ada Embeddings Model and inserted them into Pinecone DB vector database, making…
- WBWe built a voice to music AI app in 54 hours at a hackathon2012 · blog.beatmaticapp.com · ▲130
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 22d ago · stillwet.art
FastRouter.ai▲364Route requests to the right LLM for cost, latency & quality
AI · 23d ago · fastrouter.ai
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, February 2022
the whole month →
Sha256 algorithm explained online step by step visually
Life & fun · 2022 · sha256algorithm.com
EdgeDB 1.0▲947Today, after years of research, development, and refinement EdgeDB graduates to a production-ready database. We are very proud to announce EdgeDB 1.0.
Dev tools · 2022 · edgedb.com
