Add browser-local Piper WebAssembly speech

tests/voice.test.cjs

@@ -9,7 +9,7 @@ const apiWindow = {};
 vm.runInNewContext(source, {window: apiWindow, globalThis: apiWindow, Promise, String, Math, Object});
 const GameVoice = apiWindow.GameVoice;
 
-function makeHarness({supported = true, tts = true, onTranscript = () => Promise.resolve()} = {}) {
+function makeHarness({supported = true, tts = true, piper = false, onTranscript = () => Promise.resolve()} = {}) {
   const recognitions = [];
   const utterances = [];
   const states = [];
@@ -25,6 +25,17 @@ function makeHarness({supported = true, tts = true, onTranscript = () => Promise
   class Utterance {
     constructor(text) { this.text = text; utterances.push(this); }
   }
+  const audioSources = [];
+  class AudioContext {
+    constructor() { this.state = 'running'; this.destination = {}; }
+    resume() { this.state = 'running'; return Promise.resolve(); }
+    decodeAudioData() { return Promise.resolve({duration: 1}); }
+    createBufferSource() {
+      const source = {playbackRate: {value: 1}, detune: {value: 0}, connect() {}, start() { this.started = true; }, stop() { this.stopped = true; }};
+      audioSources.push(source);
+      return source;
+    }
+  }
   const synthesis = tts ? {
     spoken: [], cancelled: 0,
     getVoices: () => [{name: 'Svensk', lang: 'sv-SE'}],
@@ -37,6 +48,8 @@ function makeHarness({supported = true, tts = true, onTranscript = () => Promise
     speechSynthesis: synthesis,
     SpeechSynthesisUtterance: tts ? Utterance : undefined,
     SpeechRecognition: supported ? Recognition : undefined,
+    AudioContext,
+    GamePiper: piper ? {synthesize: () => Promise.resolve({arrayBuffer: () => Promise.resolve(new ArrayBuffer(8))})} : undefined,
   };
   vm.runInNewContext(source, {window, globalThis: window, Promise, String, Math, Object});
   const controller = window.GameVoice.createVoiceController({
@@ -45,7 +58,7 @@ function makeHarness({supported = true, tts = true, onTranscript = () => Promise
     onTranscript,
   });
   return {
-    controller, recognitions, utterances, synthesis, states, timers,
+    controller, recognitions, utterances, synthesis, states, timers, audioSources,
     runTimer(delay) {
       const match = [...timerDelays.entries()].find(([, value]) => value === delay);
       if (!match) throw new Error(`No timer found with delay ${delay}`);
@@ -223,6 +236,29 @@ test('narrator uses neutral pitch while character replies use their saved voice
   assert.ok(h.utterances[1].pitch < 1);
 });
 
+test('Piper WASM output uses the unlocked audio context and starts only after local synthesis', async () => {
+  const h = makeHarness({piper: true});
+  assert.equal(h.controller.activateFromUserGesture(), true);
+  assert.equal(h.controller.speak('Ett svar från Piper.', {role: 'narrator', voiceIdentity: 'neutral'}), true);
+  assert.equal(h.controller.getState(), 'QUEUED');
+  await new Promise(resolve => setImmediate(resolve));
+  assert.equal(h.audioSources.length, 1);
+  assert.equal(h.audioSources[0].started, true);
+  assert.equal(h.audioSources[0].detune.value, 0);
+  assert.equal(h.controller.getState(), 'SPEAKING');
+  h.audioSources[0].onended();
+  assert.equal(h.controller.getState(), 'IDLE');
+});
+
+test('Piper output keeps per-character pitch and rate stable', async () => {
+  const h = makeHarness({piper: true});
+  h.controller.activateFromUserGesture();
+  h.controller.speak('NPC-svar.', {voiceIdentity: 'masculine', characterId: 'npc-1'});
+  await new Promise(resolve => setImmediate(resolve));
+  assert.ok(h.audioSources[0].detune.value < 0);
+  assert.ok(h.audioSources[0].playbackRate.value < 1);
+});
+
 test('TTS and microphone are mutually exclusive', () => {
   const h = makeHarness();
   h.controller.update({mode: 'game-voice'});