
TVPaint Animation
The digital solution for your professional 2D animation projects.

Explore and sequence thousands of everyday sounds through machine learning visualization.

The Infinite Drum Machine, a cornerstone project from Google Creative Lab's AI Experiments, represents a significant advancement in latent space audio exploration. At its technical core, the tool utilizes t-SNE (t-Distributed Stochastic Neighbor Embedding), a dimensionality reduction technique that takes high-dimensional audio feature vectors and projects them onto a 2D plane. This process automatically clusters over 6,000 unique audio samples—ranging from household clicks to urban ambient noises—based on their sonic similarity without any human tagging. As we look towards 2026, the tool remains a primary reference for browser-based AI utility, leveraging WebGL for high-performance visualization and Tone.js for low-latency audio synthesis. Its architecture demonstrates how unsupervised learning can be applied to creative workflows, allowing users to discover 'found sounds' through spatial navigation rather than keyword searches. The machine functions as a four-track step sequencer where each voice can be dragged across the sonic map, effectively turning the entire library of sounds into a playable, infinite drum kit. It serves as both a pedagogical tool for understanding audio embeddings and a functional utility for avant-garde music production.
The Infinite Drum Machine, a cornerstone project from Google Creative Lab's AI Experiments, represents a significant advancement in latent space audio exploration.
Explore all tools that specialize in discover audio samples. This domain focus ensures Infinite Drum Machine delivers optimized results for this specific requirement.
Explore all tools that specialize in audio clustering. This domain focus ensures Infinite Drum Machine delivers optimized results for this specific requirement.
Uses t-Distributed Stochastic Neighbor Embedding to organize thousands of unlabeled audio files into a 2D map based on spectral similarity.
High-performance WebGL rendering allows for smooth exploration of thousands of audio data points in real-time.
A web-based sequencer integrated with the Tone.js library for high-precision timing and audio playback.
Algorithmic selection of new sounds within a specific geometric radius of the current marker position.
The backend extracts features like brightness and texture to determine the relative 'position' of a sound.
Runs entirely in the browser using the Web Audio API, minimizing latency and server load.
The entire codebase is available on GitHub for developers to fork and extend.
Access the application via the Google AI Experiments web portal.
Grant the browser permission to access the Web Audio API.
Allow the t-SNE visualization to initialize (loading the 2D sound map).
Use the mouse or trackpad to pan across the point cloud of audio samples.
Hover over specific nodes to trigger individual sound playback for auditioning.
Locate the four color-coded voice markers on the interface.
Drag each marker to a different cluster of sounds (e.g., 'thuds' for kicks, 'clicks' for snares).
Activate the 16-step sequencer at the bottom of the screen to create a rhythm.
Adjust the Tempo (BPM) slider to synchronize with your creative project.
Utilize the 'Shuffle' button to randomize sound selections within the current spatial neighborhoods.
All Set
Ready to go
Verified feedback from other users.
"Users praise the intuitive visual interface and the surprising musicality of random everyday sounds, though some request MIDI export."
Post questions, share tips, and help other users.

The digital solution for your professional 2D animation projects.

Empowering independent artists with digital music distribution, publishing administration, and promotional tools.

Convert creative micro-blogs into high-performance web presences using generative AI and Automattic's core infrastructure.

Fashion design technology software and machinery for apparel product development.

Instantly turns any text to natural sounding speech for listening online or generating downloadable audio.

Professional studio-quality AI headshot generator for individuals and teams.