docs: update API reference, examples table, and guide description

- Add setEmotion()/getEmotion() to llms-full.txt API Reference (V2 only)
- Fix V2 VRM mode row: getVrmFrame() supported (was "getFrame() only")
- Update Body Motion description with LoopPingPong + asymmetric crossfade
- Update guide example description: V1/V2 engine selector
- Add Guide row to README examples table
- Update comparison example description with VRM mode auto-detect

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Author: jcggl

README.md

@@ -138,9 +138,10 @@ Working examples you can run locally — zero npm install, all loaded from CDN.
 
 | Example | Description | Live Demo | Source |
 |---------|-------------|-----------|--------|
+| **Guide** | 6-step interactive tutorial with V1/V2 engine selector, VRM avatar, live demos. | [Try it](https://animasync.quasar.ggls.dev/examples/guide/) | [index.html](examples/guide/index.html) |
 | **V1 Data** | V1 phoneme engine — 52 ARKit blendshapes visualization, ONNX inference, playback. | [Try it](https://animasync.quasar.ggls.dev/examples/vanilla-basic/) | [index.html](examples/vanilla-basic/index.html) |
 | **V2 Data** | V2 emotion model — 52 ARKit blendshapes with 5-dim FiLM conditioning. | [Try it](https://animasync.quasar.ggls.dev/examples/vanilla-avatar/) | [index.html](examples/vanilla-avatar/index.html) |
-| **V1 vs V2** | Side-by-side dual avatar comparison. Same voice, two animation engines. | [Try it](https://animasync.quasar.ggls.dev/examples/vanilla-comparison/) | [index.html](examples/vanilla-comparison/index.html) |
+| **V1 vs V2** | Side-by-side dual avatar comparison with VRM mode auto-detect. | [Try it](https://animasync.quasar.ggls.dev/examples/vanilla-comparison/) | [index.html](examples/vanilla-comparison/index.html) |
 
 **Run any example:**
 

index.html

@@ -698,7 +698,7 @@ <h2 class="section-title">See it in action</h2>
         <div>
           <div class="card-badge">Interactive Guide</div>
           <h3>Build Your Own AI Talking Avatar</h3>
-          <p>6-step interactive tutorial. Download a VRM, wire up AnimaSync V1, apply lip sync, add mic streaming &mdash; with live demos at each step.</p>
+          <p>6-step interactive tutorial. Choose V1 or V2 engine, load a VRM avatar, apply lip sync, stream from mic &mdash; with live demos at each step.</p>
         </div>
         <span class="card-cta">Start Guide &#8594;</span>
       </div>

llms-full.txt

@@ -28,7 +28,7 @@ AnimaSync is a browser-native voice-to-animation engine. It takes audio input (f
 - **Lip Sync**: ONNX inference maps phonemes to ARKit blendshapes (jaw, mouth, tongue)
 - **Facial Expression**: Voice energy and pitch drive brows, cheeks, eyes, and smile
 - **Eye Animation**: Stochastic blink injection (2.5-4.5s intervals, 15% double-blink)
-- **Body Motion**: Embedded VRMA bone animation clips with idle/speaking crossfade
+- **Body Motion**: Embedded VRMA bone animation clips with LoopPingPong idle + asymmetric crossfade (0.8s in, 1.0s out)
 
 ### Technology Stack
 
@@ -126,6 +126,18 @@ Extract a VRM 18-dim frame from a ProcessResult. Converts ARKit blendshapes to V
 
 Get embedded VRMA bone animation clips for idle breathing and speaking gestures.
 
+#### `setEmotion(vector: number[]): void` (V2 only)
+
+Set a 5-dimensional emotion vector: `[neutral, joy, anger, sadness, surprise]` with values 0-1. Applied to all subsequent `processAudio`/`processAudioChunk` calls. Default: `[0, 0, 0, 0, 0]` (neutral).
+
+```javascript
+lipsync.setEmotion([0, 0.8, 0, 0, 0]); // 80% joy
+```
+
+#### `getEmotion(): number[]` (V2 only)
+
+Returns the current 5-dim emotion vector.
+
 #### `reset(): void`
 
 Clear streaming state. Call between utterances when using `processAudioChunk`.
@@ -156,7 +168,7 @@ interface ProcessResult {
 | Model architecture | Phoneme classification -> viseme mapping | Emotion model + FiLM conditioning |
 | Post-processing | OneEuroFilter + anatomical constraints | crisp_mouth + fade + auto-blink |
 | Expression generation | Built-in IdleExpressionGenerator | Blink injection in post-process |
-| VRM mode | getVrmFrame() + convert_arkit_to_vrm() for VRM 18-dim | getFrame() only (52-dim ARKit) |
+| VRM mode | getVrmFrame() + convert_arkit_to_vrm() for VRM 18-dim | getVrmFrame() for VRM 18-dim |
 | Voice activity | Built-in VoiceActivityDetector | Not included |
 | ONNX fallback | Heuristic mode (energy-based) | None (ONNX required) |
 | Emotion control | Not included | 5-dim FiLM conditioning (neutral, joy, anger, sadness, surprise) via setEmotion()/getEmotion() |
@@ -212,7 +224,7 @@ Tongue: tongueOut
 
 | Example | Description | URL |
 |---------|-------------|-----|
-| Step-by-Step Guide | 6-step interactive tutorial: VRM + AnimaSync V1 lip sync with live demos (CDN 0.4.5, VRM mode auto-detect, idle eye blink, audio-synced playback, LoopPingPong idle, asymmetric crossfade) | https://animasync.quasar.ggls.dev/examples/guide/ |
+| Step-by-Step Guide | 6-step interactive tutorial with V1/V2 engine selector, VRM mode auto-detect, idle eye blink, audio-synced playback, LoopPingPong idle, asymmetric crossfade (V1 0.4.5, V2 0.4.7) | https://animasync.quasar.ggls.dev/examples/guide/ |
 | V1 Data | V1 phoneme engine — 52 ARKit blendshapes visualization | https://animasync.quasar.ggls.dev/examples/vanilla-basic/ |
 | V2 Data | V2 emotion model — 52 ARKit with 5-dim FiLM conditioning | https://animasync.quasar.ggls.dev/examples/vanilla-avatar/ |
 | V1 vs V2 | Side-by-side dual avatar comparison | https://animasync.quasar.ggls.dev/examples/vanilla-comparison/ |