feat: voix JARVIS, Parakeet v3 pour le français, worklets audio sous CSP stricte (v2.4.1) (#19)

* feat: voix JARVIS, Parakeet v3 pour le français, worklets audio sous CSP stricte (v2.4.1)

Voix
- Timbre « JARVIS » (Web Audio) : hauteur légèrement abaissée, chaleur dans
  les basses, présence, compression douce, courte réverbération d'intercom.
  Activé par défaut, réglable dans Paramètres → Voix.
- Préréglage « Voix JARVIS » en un clic : moteur local, voix masculine
  française (Piper Tom téléchargé automatiquement, Kokoro n'ayant pas de voix
  française masculine), débit calme. Affichage de la voix active.
- Boutons Masculine / Féminine désormais lisibles (style du sélecteur ajouté).

Reconnaissance
- Parakeet TDT 0.6B v3 (NVIDIA NeMo, int8, 25 langues européennes dont le
  français) ajouté au catalogue et recommandé : plus précis et plus rapide que
  Whisper sur processeur, ponctuation incluse.
- 0,4 s de silence ajoutées avant et après chaque énoncé avant la
  reconnaissance (syllabes coupées, hallucinations de Whisper sur les clips
  courts).

Écoute permanente
- Les modules AudioWorklet sont livrés en fichiers statiques (public/worklets)
  chargés depuis l'application : en version installée, la CSP stricte
  (script-src 'self') refusait les URL blob et l'écoute permanente échouait
  avec « Unable to load a worklet's module ». Repli blob conservé pour le dev.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017Wn5VX9HNbJ7N54hR24u9Y

* docs: mesures Parakeet vs Whisper et worklets dans la feuille de route

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017Wn5VX9HNbJ7N54hR24u9Y

---------

Co-authored-by: Claude <noreply@anthropic.com>

src/services/voice/capture.ts

@@ -66,6 +66,21 @@ function getWorkletUrl(): string {
   return workletUrl;
 }
 
+/**
+ * Load an AudioWorklet module: first the static file shipped with the app (allowed by the strict
+ * CSP, script-src 'self'), then a blob URL for dev servers that do not serve /worklets.
+ */
+export async function loadWorklet(ctx: AudioContext, name: string, blobUrl: () => string): Promise<void> {
+  const staticUrl = new URL(`worklets/${name}.js`, document.baseURI).href;
+  try {
+    await ctx.audioWorklet.addModule(staticUrl);
+    return;
+  } catch (err) {
+    Log.debug('audio', `static worklet ${name} unavailable (${(err as Error).message}), trying blob`);
+  }
+  await ctx.audioWorklet.addModule(blobUrl());
+}
+
 export async function listMicrophones(): Promise<MicDevice[]> {
   try {
     const devices = await navigator.mediaDevices.enumerateDevices();
@@ -147,7 +162,7 @@ export class MicCapture {
     audioBus.setInputAnalyser(analyser);
 
     try {
-      await this.ctx.audioWorklet.addModule(getWorkletUrl());
+      await loadWorklet(this.ctx, 'eveflow-capture', getWorkletUrl);
       this.worklet = new AudioWorkletNode(this.ctx, 'eveflow-capture', { numberOfInputs: 1, numberOfOutputs: 0, channelCount: 1 });
       this.worklet.port.onmessage = (event: MessageEvent<Float32Array>) => this.onSamples(event.data);
       source.connect(this.worklet);

src/services/voice/tts.ts

@@ -29,6 +29,8 @@ export interface TtsConfig {
   localSpeaker: number;
   /** Preferred voice gender, applied to every provider's default voice. */
   voiceGender?: 'male' | 'female';
+  /** 'jarvis' adds a subtle AI timbre: slightly lower pitch, warm/crisp EQ, short room reverb. */
+  timbre?: 'natural' | 'jarvis';
 }
 
 export type TtsState = 'idle' | 'loading' | 'speaking';
@@ -255,7 +257,13 @@ export class TtsEngine {
       const source = ctx.createBufferSource();
       source.buffer = buffer;
       if (this.config.provider === 'google-free') source.playbackRate.value = Math.max(0.5, Math.min(2, this.config.speed || 1));
-      source.connect(audioBus.output);
+      if (this.config.timbre === 'jarvis') {
+        // Slightly lower and calmer, warm low end, crisp presence, a touch of room: the film's intercom feel.
+        source.playbackRate.value *= 0.94;
+        source.connect(jarvisChain(ctx));
+      } else {
+        source.connect(audioBus.output);
+      }
       const finish = () => {
         if (this.cancelCurrent === cancel) this.cancelCurrent = null;
         resolve();
@@ -334,3 +342,60 @@ export function listSystemVoices(): SpeechSynthesisVoice[] {
   if (typeof speechSynthesis === 'undefined') return [];
   return [...speechSynthesis.getVoices()].sort((a, b) => a.lang.localeCompare(b.lang) || scoreVoice(b) - scoreVoice(a));
 }
+
+let jarvisInput: AudioNode | null = null;
+let jarvisCtx: AudioContext | null = null;
+
+/** Shared effect chain for the JARVIS timbre (built once per AudioContext). */
+function jarvisChain(ctx: AudioContext): AudioNode {
+  if (jarvisInput && jarvisCtx === ctx) return jarvisInput;
+  const input = ctx.createGain();
+  const warmth = ctx.createBiquadFilter();
+  warmth.type = 'lowshelf';
+  warmth.frequency.value = 180;
+  warmth.gain.value = 3.5;
+  const presence = ctx.createBiquadFilter();
+  presence.type = 'peaking';
+  presence.frequency.value = 3200;
+  presence.Q.value = 0.9;
+  presence.gain.value = 2.5;
+  const air = ctx.createBiquadFilter();
+  air.type = 'highshelf';
+  air.frequency.value = 7000;
+  air.gain.value = -2;
+  const comp = ctx.createDynamicsCompressor();
+  comp.threshold.value = -20;
+  comp.ratio.value = 3;
+  comp.attack.value = 0.005;
+  comp.release.value = 0.12;
+  const dry = ctx.createGain();
+  dry.gain.value = 0.86;
+  const wet = ctx.createGain();
+  wet.gain.value = 0.14;
+  const reverb = ctx.createConvolver();
+  reverb.buffer = impulse(ctx, 0.22, 3.2);
+  input.connect(warmth);
+  warmth.connect(presence);
+  presence.connect(air);
+  air.connect(comp);
+  comp.connect(dry);
+  comp.connect(reverb);
+  reverb.connect(wet);
+  dry.connect(audioBus.output);
+  wet.connect(audioBus.output);
+  jarvisInput = input;
+  jarvisCtx = ctx;
+  return input;
+}
+
+/** Short synthetic room impulse (exponentially decaying noise). */
+function impulse(ctx: AudioContext, seconds: number, decay: number): AudioBuffer {
+  const rate = ctx.sampleRate;
+  const length = Math.max(1, Math.floor(rate * seconds));
+  const buffer = ctx.createBuffer(2, length, rate);
+  for (let ch = 0; ch < 2; ch++) {
+    const data = buffer.getChannelData(ch);
+    for (let i = 0; i < length; i++) data[i] = (Math.random() * 2 - 1) * Math.pow(1 - i / length, decay);
+  }
+  return buffer;
+}

src/services/voice/wakeListener.ts

@@ -7,6 +7,7 @@
 import { bridge } from '../../lib/bridge';
 import { Log } from '../../lib/log';
 import { audioBus } from './audioBus';
+import { loadWorklet } from './capture';
 import { DEFAULT_VAD, EnergyVad, type VadOptions } from './vad';
 import { buildWav16k, rms, type WavResult } from './wav';
 import type { VadEvent } from '../../../shared/voice';
@@ -103,8 +104,10 @@ export class WakeListener {
     analyser.fftSize = 512;
     source.connect(analyser);
     audioBus.setInputAnalyser(analyser);
-    if (!workletUrl) workletUrl = URL.createObjectURL(new Blob([WORKLET_SOURCE], { type: 'application/javascript' }));
-    await this.ctx.audioWorklet.addModule(workletUrl);
+    await loadWorklet(this.ctx, 'eveflow-wake', () => {
+      if (!workletUrl) workletUrl = URL.createObjectURL(new Blob([WORKLET_SOURCE], { type: 'application/javascript' }));
+      return workletUrl;
+    });
     this.node = new AudioWorkletNode(this.ctx, 'eveflow-wake', { numberOfInputs: 1, numberOfOutputs: 0, channelCount: 1 });
     this.node.port.onmessage = (event: MessageEvent<Float32Array>) => this.onSamples(event.data);
     source.connect(this.node);