digital-twin-generation
Generate photorealistic digital twins and avatar clones using each::sense AI. Create AI-powered digital representations for video calls, corporate communications, customer service, and multilingual content.
What this skill does
# Digital Twin Generation
Generate photorealistic digital twins and avatar clones using each::sense. This skill creates AI-powered digital representations of real people for video calls, corporate communications, customer service, and multilingual content delivery.
## Features
- **Photo-Based Digital Twins**: Create digital clones from reference photos
- **Photorealistic Avatars**: Generate lifelike avatar representations
- **Video Call Twins**: Digital twins optimized for virtual meetings
- **Corporate Spokespersons**: Professional digital representatives for brand communication
- **Customer Service Avatars**: Consistent AI representatives for support interactions
- **Multilingual Twins**: Digital twins that can speak multiple languages
- **Expressive Twins**: Avatars with natural facial expressions and emotions
- **Full-Body Twins**: Complete digital representations including body and gestures
- **Animated Videos**: Bring digital twins to life with video generation
- **Cross-Platform Consistency**: Maintain identical appearance across all platforms
## Quick Start
```bash
curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"messages": [{"role": "user", "content": "Create a photorealistic digital twin from these reference photos. Generate a professional headshot suitable for corporate use."}],
"model": "eachsense/beta",
"stream": true,
"image_urls": ["https://example.com/person-photo1.jpg", "https://example.com/person-photo2.jpg"],
"mode": "max"
}'
```
## Digital Twin Use Cases
| Use Case | Description | Recommended Photos |
|----------|-------------|-------------------|
| Video Calls | Virtual meeting representation | 3-5 front-facing photos |
| Corporate Spokesperson | Brand communications | 5-10 professional photos |
| Customer Service | Support avatar | 3-5 neutral expression photos |
| Multilingual Content | Translated video content | 5+ varied angle photos |
| Social Media | Consistent online presence | 5-10 diverse photos |
| Training Videos | Educational content delivery | 5+ photos with expressions |
## Use Case Examples
### 1. Create Digital Twin from Photos
Generate a digital twin based on reference photographs for consistent identity representation.
```bash
curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"messages": [{"role": "user", "content": "Create a digital twin from these reference photos. The twin should capture the exact likeness, skin tone, and facial features. Generate a high-quality portrait with professional studio lighting on a neutral gray background."}],
"model": "eachsense/beta",
"stream": true,
"image_urls": [
"https://example.com/reference-front.jpg",
"https://example.com/reference-angle.jpg",
"https://example.com/reference-side.jpg"
],
"mode": "max"
}'
```
### 2. Photorealistic Avatar Clone
Create a highly detailed photorealistic avatar for digital presence across platforms.
```bash
curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"messages": [{"role": "user", "content": "Generate a photorealistic avatar clone from these photos. The avatar should be indistinguishable from a real photograph. Include fine details like skin texture, hair strands, and eye reflections. Output as a 1:1 square format suitable for profile pictures."}],
"model": "eachsense/beta",
"stream": true,
"image_urls": [
"https://example.com/subject-photo1.jpg",
"https://example.com/subject-photo2.jpg"
],
"mode": "max"
}'
```
### 3. Digital Twin for Video Calls
Create an optimized digital twin for virtual meeting environments.
```bash
curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"messages": [{"role": "user", "content": "Create a digital twin optimized for video calls. The twin should look natural in a home office setting with soft natural lighting. Include a subtle depth-of-field blur on the background. The person should have a friendly, approachable expression suitable for professional meetings."}],
"model": "eachsense/beta",
"stream": true,
"image_urls": [
"https://example.com/ceo-headshot.jpg",
"https://example.com/ceo-casual.jpg"
],
"mode": "max",
"session_id": "videocall-twin-001"
}'
```
### 4. Corporate Spokesperson Twin
Generate a professional digital spokesperson for brand communications.
```bash
curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"messages": [{"role": "user", "content": "Create a corporate spokesperson digital twin from these executive photos. The twin should appear authoritative yet approachable. Professional business attire, confident posture, clean corporate background with subtle brand colors (navy blue). Suitable for investor presentations and company announcements."}],
"model": "eachsense/beta",
"stream": true,
"image_urls": [
"https://example.com/exec-professional.jpg",
"https://example.com/exec-speaking.jpg",
"https://example.com/exec-portrait.jpg"
],
"mode": "max"
}'
```
### 5. Customer Service Avatar
Create a consistent, friendly avatar for customer support interactions.
```bash
curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"messages": [{"role": "user", "content": "Generate a customer service avatar digital twin. The avatar should have a warm, helpful expression with a genuine smile. Professional but approachable appearance. Clean, minimal background. The twin will be used for chat support and help desk interfaces, so it should feel trustworthy and friendly."}],
"model": "eachsense/beta",
"stream": true,
"image_urls": [
"https://example.com/support-rep-photo.jpg"
],
"mode": "max"
}'
```
### 6. Multilingual Digital Twin
Create a digital twin designed for multilingual content delivery.
```bash
curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"messages": [{"role": "user", "content": "Create a digital twin for multilingual video content. Generate the twin with a neutral mouth position that works well for lip-sync dubbing. Include multiple angles: front-facing, slight left turn, and slight right turn. The lighting should be even and consistent to ensure seamless video dubbing across different languages."}],
"model": "eachsense/beta",
"stream": true,
"image_urls": [
"https://example.com/presenter-front.jpg",
"https://example.com/presenter-left.jpg",
"https://example.com/presenter-right.jpg"
],
"mode": "max",
"session_id": "multilingual-twin-project"
}'
```
### 7. Digital Twin with Expressions
Generate a digital twin with various facial expressions for dynamic content.
```bash
curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"messages": [{"role": "user", "content": "Create a digital twin with multiple expressions from these reference photos. Generate 4 varRelated 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.