good

src/config.rs

@@ -84,7 +84,7 @@ pub struct Config {
     /// per turn.
     pub filler_delay_ms: u64,
     /// TTS jitter buffer (ms) the mixer must fill before the response audio
-    /// starts playing (`TTS_PREBUFFER_MS`, default `900`). Larger values absorb
+    /// starts playing (`TTS_PREBUFFER_MS`, default `450`). Larger values absorb
     /// uneven TTS chunk arrival (fewer drop-outs) at the cost of added
     /// time-to-first-audio. The full buffer is only required at the start of a
     /// reply; after a mid-reply underrun the mixer resumes as soon as any audio
@@ -184,7 +184,7 @@ impl Default for Config {
             fillers_dir: PathBuf::from("assets/fillers"),
             filler_enabled: true,
             filler_delay_ms: 2500,
-            tts_prebuffer_ms: 900,
+            tts_prebuffer_ms: 450,
             tts_pipeline_depth: 3,
             filler_gain_idle: 1.0,
             filler_gain_duck: 0.15,

src/web/mivocero.html

@@ -89,12 +89,10 @@
   .msg.agent { align-self: flex-start; }
   .msg.agent .bubble { background: var(--bg); border: 1px solid var(--border); }
   .msg.error .bubble { border-color: var(--err); color: var(--err); }
-  .msg .bubble.pending::after {
-    content: "▍";
-    animation: blink 1s step-start infinite;
-    color: var(--accent);
-  }
-  @keyframes blink { 50% { opacity: 0; } }
+  /* Karaoke: words light up as they are spoken by the agent. */
+  .bubble.karaoke .kw { color: var(--muted); transition: color .18s ease; }
+  .bubble.karaoke .kw.done { color: var(--text); }
+  .bubble.karaoke .kw.now { color: var(--accent); text-shadow: 0 0 8px rgba(79,140,255,.55); }
   .hint { color: var(--muted); font-size: 13px; text-align: center; margin: auto; }
 
   footer { border-top: 1px solid var(--border); padding: 12px 18px; }
@@ -198,6 +196,17 @@ let playbackNode = null;
 let outputGain = null;
 let agentBubble = null;   // bubble being streamed by the assistant
 let agentText = '';       // accumulated assistant text for that bubble
+let agentWords = [];      // [{el, start}] word spans of the current reply
+let agentPlayedAt = 0;    // playback sample counter when the reply started
+let agentEnded = false;   // assistant_end received for the current reply
+let playedSamples = 0;    // cumulative samples emitted by the playback worklet
+let karaokeRAF = 0;       // requestAnimationFrame id while the reply streams
+let karaokePrevPlayed = 0;
+let karaokePrevTs = 0;
+let karaokeIdleMs = 0;
+// Approximate speaking rate used to map the audio playhead onto characters.
+// Only drives the visual highlight — the spoken audio is unaffected.
+const KARAOKE_CPS = 15;
 
 function log(msg) {
   const ts = new Date().toLocaleTimeString();
@@ -237,20 +246,95 @@ function addMessage(role, text, cls = '') {
 
 function startAgentMessage() {
   agentText = '';
+  agentWords = [];
   agentBubble = addMessage('agent', '');
-  agentBubble.classList.add('pending');
+  agentBubble.classList.add('karaoke');
+  agentPlayedAt = playedSamples;   // count only the audio spoken after this point
+  startKaraoke();
 }
 
 function appendAgentDelta(text) {
   if (!agentBubble) startAgentMessage();
   agentText += text;
-  agentBubble.textContent = agentText;
+  renderKaraoke();
+  applyKaraoke(karaokeChars());
   scrollDown(false);
 }
 
+// Rebuild the bubble as one <span> per word, keeping the whitespace between
+// them so the layout is identical to plain text.
+function renderKaraoke() {
+  if (!agentBubble) return;
+  agentWords = [];
+  agentBubble.textContent = '';
+  let idx = 0;
+  for (const tok of agentText.split(/(\s+)/)) {
+    if (tok === '') continue;
+    if (/^\s+$/.test(tok)) {
+      agentBubble.appendChild(document.createTextNode(tok));
+    } else {
+      const span = document.createElement('span');
+      span.className = 'kw';
+      span.textContent = tok;
+      agentBubble.appendChild(span);
+      agentWords.push({ el: span, start: idx });
+    }
+    idx += tok.length;
+  }
+}
+
+// Characters the playhead has "reached", from the audio actually emitted.
+function karaokeChars() {
+  const played = Math.max(0, playedSamples - agentPlayedAt);
+  return Math.floor((played / SAMPLE_RATE_OUT) * KARAOKE_CPS);
+}
+
+function applyKaraoke(chars) {
+  for (const w of agentWords) {
+    const end = w.start + w.el.textContent.length;
+    w.el.classList.toggle('done', end <= chars);
+    w.el.classList.toggle('now', w.start < chars && end > chars);
+  }
+}
+
+function startKaraoke() {
+  stopKaraoke();
+  agentEnded = false;
+  karaokePrevPlayed = playedSamples;
+  karaokeIdleMs = 0;
+  karaokePrevTs = performance.now();
+  karaokeRAF = requestAnimationFrame(karaokeTick);
+}
+
+function stopKaraoke() {
+  if (karaokeRAF) cancelAnimationFrame(karaokeRAF);
+  karaokeRAF = 0;
+}
+
+function karaokeTick(ts) {
+  karaokeRAF = 0;
+  if (!agentBubble) return;
+  const dt = ts - karaokePrevTs;
+  karaokePrevTs = ts;
+  const played = Math.max(0, playedSamples - agentPlayedAt);
+  if (played > karaokePrevPlayed) { karaokePrevPlayed = played; karaokeIdleMs = 0; }
+  else karaokeIdleMs += dt;
+
+  // Once the text has ended and the audio has drained (playback idle for a
+  // beat after it had actually started), light up anything still pending so
+  // the reply always ends fully highlighted.
+  if (agentEnded && karaokePrevPlayed > 0 && karaokeIdleMs > 600) {
+    for (const w of agentWords) { w.el.classList.add('done'); w.el.classList.remove('now'); }
+    return;
+  }
+  applyKaraoke(karaokeChars());
+  karaokeRAF = requestAnimationFrame(karaokeTick);
+}
+
 function endAgentMessage() {
-  if (agentBubble) agentBubble.classList.remove('pending');
+  stopKaraoke();
   agentBubble = null;
+  agentWords = [];
   agentText = '';
 }
 
@@ -314,6 +398,7 @@ class PlaybackProcessor extends AudioWorkletProcessor {
     this.buffering = true;
     this.underrunSamples = 0;
     this.underrunThreshold = Math.floor(sampleRate * 0.10);
+    this.played = 0;   // samples actually emitted (drives the karaoke highlight)
     this.port.onmessage = (e) => {
       const pcm = e.data;
       for (let i = 0; i < pcm.length; i++) {
@@ -337,6 +422,7 @@ class PlaybackProcessor extends AudioWorkletProcessor {
           s = this.buf[this.tail];
           this.tail = (this.tail + 1) % this.buf.length;
           this.underrunSamples = 0;
+          this.played++;
         } else {
           this.underrunSamples++;
           if (this.underrunSamples >= this.underrunThreshold) { this.buffering = true; this.underrunSamples = 0; }
@@ -345,7 +431,7 @@ class PlaybackProcessor extends AudioWorkletProcessor {
       out[i] = s;
       level += s * s;
     }
-    this.port.postMessage({ rms: Math.sqrt(level / out.length) });
+    this.port.postMessage({ rms: Math.sqrt(level / out.length), played: this.played });
     return true;
   }
 }
@@ -379,6 +465,7 @@ async function startAudio() {
 
   playbackNode = new AudioWorkletNode(audioCtx, 'playback-processor');
   playbackNode.port.onmessage = (e) => {
+    if (e.data.played !== undefined) playedSamples = e.data.played;
     if (e.data.rms !== undefined) outMeter.style.width = Math.min(100, e.data.rms * 200) + '%';
   };
   outputGain = audioCtx.createGain();
@@ -421,7 +508,7 @@ function handleServerText(text) {
       appendAgentDelta(event.text);
       break;
     case 'assistant_end':
-      endAgentMessage();
+      agentEnded = true;   // keep the bubble: karaoke finishes when audio drains
       break;
     case 'error':
       endAgentMessage();