Skip to main content
Glama

animate-to-audio

Generate After Effects keyframes from an audio file's waveform or detected beats, syncing any layer or effect property to the sound. No manual keyframe computation needed.

Instructions

Generate After Effects keyframes for a layer property directly from an audio file's waveform, in one call - no need to call analyze-audio-waveform and compute keyframes by hand first. Two modes: 'waveform' follows the amplitude envelope continuously (a VU-meter style effect - glow intensity, scale, or opacity riding the music), one keyframe per analyzed sample. 'peaks' pulses the property at each detected transient/beat and decays back to baseline (a beat-pop style effect - e.g. a logo scaling up on every kick). Accepts any audio format ffmpeg supports (mp3, m4a/aac, ogg, flac, ...) the same way analyze-audio-waveform does; uncompressed WAV needs no extra dependency. Targets a plain layer property (e.g. 'ADBE Opacity') by default, or an effect's property when effectIndex/effectName/effectMatchName is given.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNo'waveform' (default): continuous amplitude-follow. 'peaks': discrete pulse-and-decay at each detected transient.
curveNoResponse shaping (default: linear). 'exponential' emphasizes loud peaks (punchier); 'logarithmic' boosts quiet-passage detail. In 'peaks' mode this only affects velocitySensitivePeaks scaling.
compNameNoName of the target composition. Preferred over compIndex when both are given.
filePathYesAbsolute path to the audio file (obtained from get-audio-info sourceFilePath).
compIndexNo1-based composition index, used if compName is not given.
layerNameNoName of the target layer (alternative to layerIndex).
numPointsNoWaveform samples to analyze, each becoming one keyframe in 'waveform' mode (default: 100). Ignored for keyframe generation in 'peaks' mode (still used to detect the peaks themselves), where the number of keyframes instead follows how many transients are detected. Kept well below analyze-audio-waveform's own cap since every point here becomes a real After Effects keyframe.
outputMaxYesProperty value at full amplitude (waveform amplitude 1, or peaks-mode value at the instant of a hit).
outputMinYesProperty value at silence/rest (waveform amplitude 0, or peaks-mode baseline between hits).
startTimeNoSeconds to offset every generated keyframe by, to start the animation partway through the comp (default: 0).
effectNameNoDisplay name of the effect to target.
layerIndexNo1-based index of the target layer within the composition.
effectIndexNo1-based index of the effect in the layer's Effects group, to target an effect property instead of a plain layer property.
propertyNameNoTarget property name or matchName (e.g. 'ADBE Opacity', 'ADBE Scale', 'ADBE Rotate Z' - matchNames are locale-independent and preferred). Used when propertyPath is not given, or as the effect-property fallback.
propertyPathNoPath to the target property, from the effect root (if an effect selector is given) or from the layer root otherwise, e.g. ['Compositing Options', 'Effect Opacity'] or [3, 1].
clearExistingNoRemove the property's existing keyframes first (default: true).
propertyIndexNoFallback target property index under the effect root (effect targeting only).
effectMatchNameNoInternal matchName of the effect to target.
keyframeOptionsNoOptional graph/easing controls applied uniformly to every keyframe this call generates.
smoothingWindowNoWaveform mode only: moving-average window (in samples) to smooth out jittery amplitude before keyframing (default: 3, use 1 to disable).
peakDecaySecondsNoPeaks mode only: seconds to fall back to outputMin after each hit (default: 0.15).
velocitySensitivePeaksNoPeaks mode only: scale each hit's height by how loud that specific transient was, instead of every hit jumping to the same outputMax (default: true).
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the transparency burden and handles it well. It discloses mode-specific behaviors (continuous waveform following vs. pulse-and-decay peaks), keyframe generation details (one per sample), and property targeting (plain layer vs. effect property). It also notes format dependencies, though it stops short of mentioning undo or error handling.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is a dense but well-structured paragraph: purpose, then modes, then compatibility and targeting. Every sentence contributes useful information without fluff, and the length is appropriate for the tool's complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 22 parameters and no output schema, the description covers all critical aspects: main purpose, mode semantics, supported audio formats, and property targeting. It could mention preconditions like composition existence, but overall it is highly complete for the given complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description adds value beyond the schema by explaining how numPoints maps directly to keyframe count and is intentionally capped lower than analyze-audio-waveform. It also clarifies how curve affects peaks mode, enhancing parameter understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Generate After Effects keyframes for a layer property directly from an audio file's waveform, in one call.' It clearly distinguishes itself from the sibling analyze-audio-waveform by saying 'no need to call analyze-audio-waveform and compute keyframes by hand first,' and elaborates on two modes to clarify its scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides explicit usage context, explaining when to use it (for audio-driven keyframes) and describing two modes with example effects. It references the sibling analyze-audio-waveform for format compatibility. While it doesn't explicitly enumerate alternatives like setLayerKeyframe, it clearly implies this is the preferred automated approach versus manual keyframing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/omar-hesham/after-effect-mcp-with-claude'

If you have feedback or need assistance with the MCP directory API, please join our Discord server