web-audio-api
Web Audio API for JARVIS audio feedback and voice processing
What this skill does
# Web Audio API Skill
## 1. Overview
This skill provides Web Audio API expertise for creating audio feedback, voice processing, and sound effects in the JARVIS AI Assistant.
**Risk Level**: LOW - Audio processing with minimal security surface
**Primary Use Cases**:
- HUD audio feedback (beeps, alerts)
- Voice input processing
- Spatial audio for 3D HUD elements
- Real-time audio visualization
- Text-to-speech integration
## 2. Core Responsibilities
### 2.1 Fundamental Principles
1. **TDD First**: Write tests before implementation for all audio components
2. **Performance Aware**: Optimize for 60fps with minimal audio latency
3. **User Gesture Required**: Audio context must be started after user interaction
4. **Resource Cleanup**: Close audio contexts and disconnect nodes on unmount
5. **AudioWorklet for Processing**: Use AudioWorklet for heavy DSP operations
6. **Accessibility**: Provide visual alternatives to audio feedback
7. **Volume Control**: Respect system and user volume preferences
8. **Error Handling**: Gracefully handle audio permission denials
## 3. Technology Stack & Versions
### 3.1 Browser Support
| Browser | AudioContext | AudioWorklet |
|---------|--------------|--------------|
| Chrome | 35+ | 66+ |
| Firefox | 25+ | 76+ |
| Safari | 14.1+ | 14.1+ |
### 3.2 TypeScript Types
```typescript
// types/audio.ts
interface AudioFeedbackOptions {
frequency: number
duration: number
type: OscillatorType
volume: number
}
interface SpatialAudioPosition {
x: number
y: number
z: number
}
```
## 4. Implementation Patterns
### 4.1 Audio Context Management
```typescript
// composables/useAudioContext.ts
export function useAudioContext() {
const audioContext = ref<AudioContext | null>(null)
const isInitialized = ref(false)
async function initialize() {
if (audioContext.value) return
audioContext.value = new AudioContext()
if (audioContext.value.state === 'suspended') await audioContext.value.resume()
isInitialized.value = true
}
onUnmounted(() => {
audioContext.value?.close()
audioContext.value = null
})
return { audioContext: readonly(audioContext), isInitialized: readonly(isInitialized), initialize }
}
```
### 4.2 HUD Beep Feedback
```typescript
// composables/useHUDSounds.ts
export function useHUDSounds() {
const { audioContext, initialize } = useAudioContext()
async function playBeep(options: Partial<AudioFeedbackOptions> = {}) {
await initialize()
const ctx = audioContext.value
if (!ctx) return
const { frequency = 440, duration = 0.1, type = 'sine', volume = 0.3 } = options
const safeVolume = Math.max(0, Math.min(1, volume))
const oscillator = ctx.createOscillator()
const gainNode = ctx.createGain()
oscillator.type = type
oscillator.frequency.value = frequency
gainNode.gain.value = safeVolume
gainNode.gain.exponentialRampToValueAtTime(0.001, ctx.currentTime + duration)
oscillator.connect(gainNode).connect(ctx.destination)
oscillator.start()
oscillator.stop(ctx.currentTime + duration)
}
const sounds = {
confirm: () => playBeep({ frequency: 880, duration: 0.1, volume: 0.2 }),
alert: () => playBeep({ frequency: 440, duration: 0.3, type: 'square', volume: 0.4 }),
error: () => playBeep({ frequency: 220, duration: 0.5, type: 'sawtooth', volume: 0.3 }),
click: () => playBeep({ frequency: 1000, duration: 0.05, volume: 0.1 })
}
return { playBeep, sounds }
}
```
### 4.3 Audio Visualization
```typescript
// composables/useAudioVisualization.ts
export function useAudioVisualization() {
const { audioContext, initialize } = useAudioContext()
let analyser: AnalyserNode | null = null
let dataArray: Uint8Array | null = null
async function setupAnalyser(source: AudioNode) {
await initialize()
const ctx = audioContext.value
if (!ctx) return
analyser = ctx.createAnalyser()
analyser.fftSize = 256
dataArray = new Uint8Array(analyser.frequencyBinCount)
source.connect(analyser)
}
function getFrequencyData(): Uint8Array | null {
if (!analyser || !dataArray) return null
analyser.getByteFrequencyData(dataArray)
return dataArray
}
return { setupAnalyser, getFrequencyData }
}
```
### 4.4 Spatial Audio for 3D HUD
```typescript
// composables/useSpatialAudio.ts
export function useSpatialAudio() {
const { audioContext, initialize } = useAudioContext()
let panner: PannerNode | null = null
async function createSpatialSource(position: SpatialAudioPosition) {
await initialize()
const ctx = audioContext.value
if (!ctx) return null
panner = ctx.createPanner()
panner.panningModel = 'HRTF'
panner.distanceModel = 'inverse'
setPosition(position)
return panner
}
function setPosition(pos: SpatialAudioPosition) {
if (!panner) return
panner.positionX.value = pos.x
panner.positionY.value = pos.y
panner.positionZ.value = pos.z
}
return { createSpatialSource, setPosition }
}
```
### 4.5 Microphone Input
```typescript
// composables/useMicrophone.ts
export function useMicrophone() {
const { audioContext, initialize } = useAudioContext()
const stream = ref<MediaStream | null>(null)
const isListening = ref(false)
const error = ref<string | null>(null)
async function startListening() {
try {
await initialize()
stream.value = await navigator.mediaDevices.getUserMedia({
audio: { echoCancellation: true, noiseSuppression: true, autoGainControl: true }
})
isListening.value = true
return stream.value
} catch (err) {
error.value = err instanceof Error ? err.message : 'Microphone access denied'
return null
}
}
function stopListening() {
stream.value?.getTracks().forEach(track => track.stop())
stream.value = null
isListening.value = false
}
onUnmounted(() => stopListening())
return { stream: readonly(stream), isListening: readonly(isListening), error: readonly(error), startListening, stopListening }
}
```
## 5. Implementation Workflow (TDD)
### Step 1: Write Failing Test First
```typescript
// tests/composables/useHUDSounds.test.ts
import { describe, it, expect, vi, beforeEach } from 'vitest'
import { useHUDSounds } from '~/composables/useHUDSounds'
// Mock AudioContext nodes
const mockOscillator = { connect: vi.fn(), start: vi.fn(), stop: vi.fn(), frequency: { value: 440 } }
const mockGainNode = { connect: vi.fn(), gain: { value: 1, exponentialRampToValueAtTime: vi.fn() } }
const mockAudioContext = {
state: 'running', currentTime: 0, destination: {},
createOscillator: vi.fn(() => mockOscillator),
createGain: vi.fn(() => mockGainNode),
resume: vi.fn(), close: vi.fn()
}
vi.stubGlobal('AudioContext', vi.fn(() => mockAudioContext))
describe('useHUDSounds', () => {
beforeEach(() => vi.clearAllMocks())
it('creates oscillator with correct frequency', async () => {
const { playBeep } = useHUDSounds()
await playBeep({ frequency: 880 })
expect(mockOscillator.frequency.value).toBe(880)
})
it('clamps volume to valid range', async () => {
const { playBeep } = useHUDSounds()
await playBeep({ volume: 2.5 })
expect(mockGainNode.gain.value).toBeLessThanOrEqual(1)
})
it('connects nodes in correct order', async () => {
const { playBeep } = useHUDSounds()
await playBeep()
expect(mockOscillator.connect).toHaveBeenCalledWith(mockGainNode)
expect(mockGainNode.connect).toHaveBeenCalledWith(mockAudioContext.destination)
})
})
```
### Step 2: Implement Minimum to Pass
```typescript
// composables/useHUDSounds.ts
export function useHUDSounds() {
// Implementation from section 4.2
// Only add features that tests require
}
```
### Step 3: Refactor Following Patterns
After tests pass, refactor to:
- Extract shared audio context logic
- Add proper TypeScript types
- Implement cleanup on unmount
### Step 4: Run Full Verification
```bash
# Run all audio-related tests
npm tesRelated in Image & Video
watch
IncludedWatch a video (URL or local path). Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, pulls the transcript from captions (or Whisper API fallback), and hands the result to Claude so it can answer questions about what's in the video.
physical-ai-defect-image-generation
IncludedUse when the user wants to orchestrate defect image generation, run associated setup, or handle outputs on OSMO. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images. This skill helps with first-time asset setup, creation of finetuning checkpoints, and configuring deployment. Trigger keywords: defect image generation, dig workflow, dig pipeline, defect image detection workflow, aoi pipeline, aoi anomalygen, usd2roi anomalygen, day 0 pcba, day 1 pcba, day 1 real-photo alignment, day 1 manual roi, metal surface anomaly, glass defect, anomalygen finetune, setup_pcb, setup_metal, setup_glass, setup_pretrained, dig setup, dig datasets, dig pretrained checkpoint, dig image-edit endpoint.
accelint-react-best-practices
IncludedReact performance optimization and best practices. ALWAYS use this skill when working with any React code - writing components, hooks, JSX; refactoring; optimizing re-renders, memoization, state management; reviewing for performance; fixing hydration mismatches; debugging infinite re-renders, stale closures, input focus loss, animations restarting; preventing remounting; implementing transitions, lazy initialization, effect dependencies. Even simple React tasks benefit from these patterns. Covers React 19+ (useEffectEvent, Activity, ref props). Triggers - useEffect, useState, useMemo, useCallback, memo, inline components, nested components, components inside components, re-render, performance, hydration, SSR, Next.js, useDeferredValue, combined hooks.
elevenlabs-agents
IncludedBuild conversational AI voice agents with ElevenLabs Platform using React, JavaScript, React Native, or Swift SDKs. Configure agents, tools (client/server/MCP), RAG knowledge bases, multi-voice, and Scribe real-time STT. Use when: building voice chat interfaces, implementing AI phone agents with Twilio, configuring agent workflows or tools, adding RAG knowledge bases, testing with CLI "agents as code", or troubleshooting deprecated @11labs packages, Android audio cutoff, CSP violations, dynamic variables, or WebRTC config. Keywords: ElevenLabs Agents, ElevenLabs voice agents, AI voice agents, conversational AI, @elevenlabs/react, @elevenlabs/client, @elevenlabs/react-native, @elevenlabs/elevenlabs-js, @elevenlabs/agents-cli, elevenlabs SDK, voice AI, TTS, text-to-speech, ASR, speech recognition, turn-taking model, WebRTC voice, WebSocket voice, ElevenLabs conversation, agent system prompt, agent tools, agent knowledge base, RAG voice agents, multi-voice agents, pronunciation dictionary, voice speed control, elevenlabs scribe, @11labs deprecated, Android audio cutoff, CSP violation elevenlabs, dynamic variables elevenlabs, case-sensitive tool names, webhook authentication
humanizer
IncludedHumanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 28 pattern detectors, 560+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural/human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.
generating-mermaid-diagrams
IncludedSalesforce architecture diagrams using Mermaid with ASCII fallback. Use this skill when generating text-based diagrams for Salesforce architecture, OAuth flows, ERDs, integration sequences, or Agentforce structure. TRIGGER when: user says "diagram", "visualize", "ERD", or asks for sequence diagrams, flowcharts, class diagrams, or architecture visualizations in Mermaid. DO NOT TRIGGER when: user wants PNG/SVG image output (use generating-visual-diagrams), or asks about non-Salesforce systems.