voice
Voice recognition, wake words, and voice-controlled trading
What this skill does
# Voice - Complete API Reference
Voice-controlled interface with wake word detection, speech-to-text, and text-to-speech.
---
## Chat Commands
### Voice Control
```
/voice start Start voice listening
/voice stop Stop voice listening
/voice status Check voice status
/voice wake "hey clodds" Set wake word
```
### Settings
```
/voice language en-US Set language
/voice sensitivity high Wake word sensitivity
/voice timeout 30 Silence timeout (seconds)
/voice continuous on Enable continuous mode
```
---
## TypeScript API Reference
### Create Voice Assistant
```typescript
import { createVoiceAssistant } from 'clodds/voice';
const voice = createVoiceAssistant({
// Wake word
wakeWord: 'hey clodds',
wakeWordSensitivity: 0.5, // 0-1
// Speech-to-text
stt: {
provider: 'whisper', // 'whisper' | 'vosk' | 'google'
model: 'base', // 'tiny' | 'base' | 'small' | 'medium' | 'large'
language: 'en',
},
// Text-to-speech
tts: {
provider: 'elevenlabs', // 'elevenlabs' | 'say' | 'espeak'
voice: 'rachel',
speed: 1.0,
},
// Timeouts
silenceTimeoutMs: 3000,
maxRecordingMs: 30000,
});
```
### Start/Stop Listening
```typescript
// Start listening for wake word
await voice.start();
// Check if listening
const isListening = voice.isListening();
// Stop listening
await voice.stop();
```
### Event Handlers
```typescript
// Wake word detected
voice.on('wake', () => {
console.log('Wake word detected!');
});
// Speech recognized
voice.on('speech', (text: string) => {
console.log(`User said: ${text}`);
});
// Transcription complete
voice.on('transcript', (result) => {
console.log(`Final: ${result.text}`);
console.log(`Confidence: ${result.confidence}`);
console.log(`Duration: ${result.durationMs}ms`);
});
// Error handling
voice.on('error', (error) => {
console.error('Voice error:', error);
});
// Silence detected
voice.on('silence', () => {
console.log('User stopped speaking');
});
```
### Speak (TTS)
```typescript
// Speak text
await voice.speak('Your order has been placed');
// Speak with options
await voice.speak('Market is up 5%', {
voice: 'josh',
speed: 1.2,
pitch: 1.0,
});
// Cancel speaking
voice.cancelSpeech();
```
### Manual Transcription
```typescript
// Transcribe audio buffer
const result = await voice.transcribe(audioBuffer, {
language: 'en',
prompt: 'Trading commands', // Context hint
});
console.log(`Text: ${result.text}`);
console.log(`Language: ${result.language}`);
```
### Voice Activity Detection
```typescript
// Check if user is speaking
const vad = voice.getVAD();
vad.on('speechStart', () => {
console.log('User started speaking');
});
vad.on('speechEnd', (audio) => {
console.log('User stopped speaking');
// audio contains the recorded speech
});
```
---
## Wake Word Configuration
| Setting | Values | Description |
|---------|--------|-------------|
| `wakeWord` | Any phrase | Trigger phrase |
| `sensitivity` | 0.0 - 1.0 | Detection threshold |
**Built-in wake words:**
- "hey clodds"
- "okay clodds"
- "clodds"
---
## STT Providers
| Provider | Quality | Speed | Offline |
|----------|---------|-------|---------|
| **Whisper** | Excellent | Medium | Yes |
| **Vosk** | Good | Fast | Yes |
| **Google** | Excellent | Fast | No |
---
## TTS Providers
| Provider | Quality | Voices | API Key |
|----------|---------|--------|---------|
| **ElevenLabs** | Premium | 30+ | Required |
| **say** (macOS) | Good | System | None |
| **espeak** | Basic | Many | None |
---
## Voice Commands Examples
Once voice is active, speak naturally:
```
"Hey Clodds, what's my portfolio value?"
"Hey Clodds, buy 100 dollars of Trump YES"
"Hey Clodds, what are the top arbitrage opportunities?"
"Hey Clodds, set a price alert for Bitcoin at 100k"
```
---
## Best Practices
1. **Quiet environment** — Background noise affects accuracy
2. **Clear speech** — Speak clearly for best recognition
3. **Short commands** — Keep voice commands concise
4. **Confirmation** — Enable confirmations for trades
5. **Fallback** — Text input always available
Related 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.