app.nzapp
AppsProjectsReposPullsChatIntegrationsGatewayModelsEvalsToolsDatasetsMCPDeploysPricingBlogDocsAssistantsCharactersArtMusic
Sign inStart building
Agent stack
Cloud coding agentAgents SDKIntegrationsBrowser agentMonitors & auto-agentsSchedulersAgent skillsMCP serversDeep research
Models & API
AI GatewayModel catalogModel evalsModel spacesPlaygroundText to imageImage to 3DText to 3DMusic & SFXAudio editorMedia optimizerAI art & libraryChatAPI referenceSchemaBecome a provider
Compute & hosting
DeploysAddonsPostgres hostinggobed vector searchSite hostingAnalyticsCog GPU hostingRL trainingBuilds & CIWorkersTask queuesDomainsGit hosting
Tools
AI toolsDrawDiffusion canvasLive DrawWriteSheetsArtifactsVideo studioNotebooksDatasets
Learn
DocsBlogEval guidesPrompt libraryCLIAlternativesPapersAI charactersArt gallerySecurityConsulting
Company
PricingEnterpriseSettingsBillingStatusInvestorsCreate accountTerms of ServicePrivacy Policy
app.nzapp.nz

AI agent cloud for coding, deploys, model routing, and research. Built for teams shipping software.

Built in New Zealand by App AI NZ.

Social
X / TwitterGitHubYouTube
The app.nz network
GpuBrainPapersReading TimemojojojoNetwrckText-Generator.ioCodex InfinityOpenPathsCuteDSLAI Art GeneratorAIArt-Generator.artSiteSimSimplexGenDictatorFlowWebFiddleRing.nzChatGibidyBitBankExperimentFlowEvangelerHires.nzHow.nzV5 GamesAddicting Word GamesBig Multiplayer ChessWord SmashingreWord GameMultiplication Master
© 2026 App AI NZ Ltd. All rights reserved.All systems normalTermsPrivacy
Blog
July 22, 2026·9 min read·app.nz

ComfyUI lab 5: Turn sound into reactive motion

Window a waveform, measure local energy or spectrum, map it to frames, and preserve synchronization at a declared FPS.

Listen to this article

On-device voice

Uses the voice built into your browser; no article text leaves this page.

Audio narration is not supported by this browser.

Audio reactivity is signal mapping, not magic. A waveform is amplitude over time. Animation is a sequence of frames. The workflow’s job is to summarize the right slice of audio for each frame and map that measurement into a visual parameter.

Time is the shared coordinate

At 12 fps, frame 24 represents two seconds. Split the waveform into frame-aligned windows. RMS energy gives a stable loudness estimate; a short-time Fourier transform separates bass, midrange, and treble; onset detection finds transients. The included MIT node offers three small baselines: waveform, spectrum bars, and an RMS-driven pulse.

The graph caps duration and frame count deliberately. A 60-second clip at 60 fps is 3,600 full-resolution images, which can exhaust ordinary RAM even without diffusion. Prototype six seconds at 12 fps, prove timing, then raise quality.

Map signals musically

Raw values flicker. Normalize against a rolling percentile, add attack/release smoothing, and use different bands for different controls: bass for scale, snare-band transients for cuts, vocals for color. The advanced MIT RyanOnTheInside pack extends this idea to MIDI, masks, particles, optical flow, and model conditioning. AnimateDiff Evolved can receive scheduled influence after the signal layer is understood.

Export audio beside the animation and verify duration exactly. A beautiful reactive render that drifts a frame every few seconds is still broken.

Run the lab

  • Open this graph in Comfy Studio
  • Download the exact API-format workflow
  • CLI: app comfy download audio-reactive-visualizer

Record the graph JSON, input assets, seed where relevant, model or service version, custom-node commit, and final artifact together. That bundle—not a screenshot—is the reproducible creative unit.

Open-source map

  • Open app.nz reactive node — MIT minimal renderer used by the graph
  • RyanOnTheInside — MIT advanced audio, MIDI, masks, particles, and motion
  • AnimateDiff Evolved — Apache-2.0 diffusion animation system

Creative Systems Labs: 5 of 12. Previous: Build a talking character pipeline Next: Build style as a system

Build what you just read

Ship agents, models, and apps on one cloud.

Start with free credits, then use the same platform from the web app, CLI, desktop app, or MCP.

Start building freeRead the docs

Keep reading

ComfyUI lab 1: Design sound effects from first principles

Translate source, action, material, space, microphone, and timing into a reproducible SFX graph.

ComfyUI lab 8: Prototype frame transforms safely

Understand image tensor shape, range, batch semantics, and the boundary between a prototype code block and a maintained node.

ComfyUI lab 12: Turn a concept image into a 3D asset

Prepare an object reference that communicates shape cleanly, then validate the generated asset outside the preview renderer.