@omote/core 0.6.4 → 0.7.1

package/README.md

@@ -5,10 +5,13 @@
 ## Features
 
 - **Lip Sync (A2E)** — Audio to 52 ARKit blendshapes via Wav2Vec2, with automatic GPU/CPU platform detection
-- **Full-Face Pipeline** — TTS audio playback to lip sync with ExpressionProfile scaling, gapless scheduling
+- **PlaybackPipeline** — TTS audio playback to lip sync with ExpressionProfile scaling, gapless scheduling
 - **Speech Recognition** — SenseVoice ASR (ONNX), 15x faster than Whisper, progressive transcription
 - **Voice Activity Detection** — Silero VAD with Worker and main-thread modes
-- **Text-to-Speech** — ChatterboxTurbo (experimental, use server-side TTS for production)
+- **Text-to-Speech** — Kokoro TTS (82M q8, experimental) with TTSBackend interface for custom engines
+- **CharacterController** — Renderer-agnostic avatar composition (compositor + gaze + life layer)
+- **TTSPlayback** — Composes TTSBackend + PlaybackPipeline for text → lip sync
+- **VoicePipeline** — Full conversational agent loop with local TTS support (cloud or offline)
 - **Animation Graph** — State machine (idle/listening/thinking/speaking) with emotion blending
 - **Emotion Controller** — Preset-based emotion system with smooth transitions
 - **Model Caching** — IndexedDB with versioning, LRU eviction, and quota monitoring
@@ -27,34 +30,33 @@ Peer dependency: `onnxruntime-web` is included — no additional installs needed
 
 ## Quick Start
 
-### FullFacePipeline (TTS Lip Sync)
+### PlaybackPipeline (TTS Lip Sync)
 
 The most common use case: feed TTS audio chunks and get back 52 ARKit blendshape frames at render rate.
 
 ```typescript
-import { FullFacePipeline, createA2E } from '@omote/core';
+import { PlaybackPipeline, createA2E } from '@omote/core';
 
 // 1. Create A2E backend (auto-detects GPU vs CPU)
 const lam = createA2E(); // auto-detects GPU vs CPU, fetches from HF CDN (192MB fp16)
 await lam.load();
 
 // 2. Create pipeline with expression profile
-const pipeline = new FullFacePipeline({
+const pipeline = new PlaybackPipeline({
   lam,
   sampleRate: 16000,
   profile: { mouth: 1.0, jaw: 1.0, brows: 0.6, eyes: 0.0, cheeks: 0.5, nose: 0.3, tongue: 0.5 },
 });
-await pipeline.initialize();
 
 // 3. Listen for blendshape frames
-pipeline.on('full_frame_ready', (frame) => {
+pipeline.on('frame', (frame) => {
   applyToAvatar(frame.blendshapes); // ExpressionProfile-scaled, 52 ARKit weights
 });
 
 // 4. Feed TTS audio and play
 pipeline.start();
-await pipeline.onAudioChunk(ttsAudioChunk); // Uint8Array PCM16
-await pipeline.end(); // Flush remaining audio
+pipeline.feedBuffer(ttsAudioChunk); // Uint8Array PCM16
+pipeline.end(); // Flush remaining audio
 ```
 
 ## API Reference
@@ -87,29 +89,28 @@ const { blendshapes } = await lam.infer(audioSamples);
 const jawOpen = blendshapes[LAM_BLENDSHAPES.indexOf('jawOpen')];
 ```
 
-### FullFacePipeline
+### PlaybackPipeline
 
 End-to-end TTS playback with lip sync inference, audio scheduling, and ExpressionProfile scaling.
 
 ```typescript
-import { FullFacePipeline } from '@omote/core';
+import { PlaybackPipeline } from '@omote/core';
 
-const pipeline = new FullFacePipeline({
+const pipeline = new PlaybackPipeline({
   lam,                // A2E backend from createA2E()
   sampleRate: 16000,
   profile: { mouth: 1.0, jaw: 1.0, brows: 0.6, eyes: 0.0, cheeks: 0.5, nose: 0.3, tongue: 0.5 },
 });
-await pipeline.initialize();
 
-pipeline.on('full_frame_ready', (frame) => {
+pipeline.on('frame', (frame) => {
   // frame.blendshapes    — ExpressionProfile-scaled
   // frame.rawBlendshapes — unscaled original values
   applyToAvatar(frame.blendshapes);
 });
 
 pipeline.start();
-await pipeline.onAudioChunk(chunk); // feed TTS audio (Uint8Array PCM16)
-await pipeline.end();               // flush final partial chunk
+pipeline.feedBuffer(chunk); // feed TTS audio (Uint8Array PCM16)
+pipeline.end();             // flush final partial chunk
 ```
 
 ### A2EProcessor

package/dist/{Logger-I_k4sGhM.d.mts → Logger-DSoGAYJu.d.mts}

@@ -138,4 +138,4 @@ declare const noopLogger: ILogger;
  */
 declare function getNoopLogger(): ILogger;
 
-export { DEFAULT_LOGGING_CONFIG as D, type ILogger as I, type LogFormatter as L, type LogLevel as a, type LogEntry as b, type LogSink as c, type LoggingConfig as d, LOG_LEVEL_PRIORITY as e, configureLogging as f, getLoggingConfig as g, setLoggingEnabled as h, createLogger as i, clearLoggerCache as j, getNoopLogger as k, noopLogger as n, resetLoggingConfig as r, setLogLevel as s };
+export { DEFAULT_LOGGING_CONFIG as D, type ILogger as I, type LogFormatter as L, LOG_LEVEL_PRIORITY as a, type LogEntry as b, type LogLevel as c, type LogSink as d, type LoggingConfig as e, clearLoggerCache as f, configureLogging as g, createLogger as h, getLoggingConfig as i, getNoopLogger as j, setLoggingEnabled as k, noopLogger as n, resetLoggingConfig as r, setLogLevel as s };

package/dist/{Logger-I_k4sGhM.d.ts → Logger-DSoGAYJu.d.ts}

@@ -138,4 +138,4 @@ declare const noopLogger: ILogger;
  */
 declare function getNoopLogger(): ILogger;
 
-export { DEFAULT_LOGGING_CONFIG as D, type ILogger as I, type LogFormatter as L, type LogLevel as a, type LogEntry as b, type LogSink as c, type LoggingConfig as d, LOG_LEVEL_PRIORITY as e, configureLogging as f, getLoggingConfig as g, setLoggingEnabled as h, createLogger as i, clearLoggerCache as j, getNoopLogger as k, noopLogger as n, resetLoggingConfig as r, setLogLevel as s };
+export { DEFAULT_LOGGING_CONFIG as D, type ILogger as I, type LogFormatter as L, LOG_LEVEL_PRIORITY as a, type LogEntry as b, type LogLevel as c, type LogSink as d, type LoggingConfig as e, clearLoggerCache as f, configureLogging as g, createLogger as h, getLoggingConfig as i, getNoopLogger as j, setLoggingEnabled as k, noopLogger as n, resetLoggingConfig as r, setLogLevel as s };