feat: voix Edge neuronales, Supertonic 3 en local et genre respecté par tous les moteurs (v2.5.0)

- Nouveau moteur « Microsoft Edge » (voix neuronales gratuites, sans clé) : Henri / Denise
  par défaut selon le genre, liste des voix fr-FR / fr-CA / fr-CH / fr-BE, WebSocket signé
  (Sec-MS-GEC) dans le processus principal, MP3 24 kHz. Moteur par défaut des nouvelles
  installations.
- Supertonic 3 ajouté au catalogue local (31 langues, 5 voix masculines + 5 féminines,
  44 kHz, 129 Mo) : langue transmise au worker, genres des voix vérifiés par mesure de F0.
- Kokoro déclassé pour le français (une seule voix féminine, accent) ; le choix
  masculin/féminin bascule sur le meilleur modèle installé et conserve le genre quand on
  change de modèle ; Google Translate signalé comme voix féminine uniquement.
- Deux préréglages JARVIS : en ligne (Edge Henri) et hors ligne (Supertonic 3).
- Traitement du micro par Chromium (écho, bruit, gain) débrayable pour de meilleures
  transcriptions au casque.
- Tests : protocole Edge (jeton, SSML, trames), sélection de voix ; README et feuille de
  route (mesures Supertonic, Parakeet vs Qwen3-ASR).

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MMpgFriwxiBgurUVb21oCE

tests/edgeTts.test.ts

@@ -0,0 +1,90 @@
+import { describe, expect, it } from 'vitest';
+import {
+  defaultEdgeVoice,
+  edgeConfigMessage,
+  edgeRate,
+  edgeSsml,
+  edgeSsmlMessage,
+  edgeTextFramePath,
+  edgeTokenInput,
+  edgeVoiceGender,
+  escapeXml,
+  parseEdgeBinaryFrame
+} from '../shared/edgeTts';
+
+describe('edge token input', () => {
+  it('uses Windows file time rounded down to 5 minutes followed by the client token', () => {
+    // 2026-09-04T15:23:47Z → 15:20:00Z = 1788535200 s since 1970 → +11644473600 = 13433008800 s → ×1e7 ticks.
+    const nowMs = Date.UTC(2026, 8, 4, 15, 23, 47);
+    expect(edgeTokenInput(nowMs)).toBe('1343300880000000006A5AA1D4EAFF4E9FB37E23D68491D6F4');
+  });
+  it('is stable inside a 5-minute window and applies the clock skew', () => {
+    const a = edgeTokenInput(Date.UTC(2026, 8, 4, 15, 20, 1));
+    const b = edgeTokenInput(Date.UTC(2026, 8, 4, 15, 24, 59));
+    expect(a).toBe(b);
+    expect(edgeTokenInput(Date.UTC(2026, 8, 4, 15, 20, 1), 300)).not.toBe(a);
+  });
+});
+
+describe('edge ssml', () => {
+  it('escapes text and derives the language from the voice', () => {
+    const ssml = edgeSsml('Tom & Jerry <3 "ok"', 'fr-FR-HenriNeural', 1.25);
+    expect(ssml).toContain("xml:lang='fr-FR'");
+    expect(ssml).toContain("<voice name='fr-FR-HenriNeural'>");
+    expect(ssml).toContain("rate='+25%'");
+    expect(ssml).toContain('Tom &amp; Jerry &lt;3 &quot;ok&quot;');
+    expect(escapeXml("l'été")).toBe('l&apos;été');
+  });
+  it('formats rates with a sign', () => {
+    expect(edgeRate(1)).toBe('+0%');
+    expect(edgeRate(0.8)).toBe('-20%');
+    expect(edgeRate(3)).toBe('+100%');
+  });
+  it('builds the config and ssml messages with the expected headers', () => {
+    const date = new Date(Date.UTC(2026, 8, 4, 15, 23, 47));
+    const config = edgeConfigMessage(date);
+    expect(config.startsWith('X-Timestamp:Fri, 04 Sep 2026 15:23:47 GMT+0000 (Coordinated Universal Time)\r\n')).toBe(true);
+    expect(config).toContain('Path:speech.config\r\n\r\n{');
+    expect(config).toContain('audio-24khz-48kbitrate-mono-mp3');
+    const ssml = edgeSsmlMessage('abc123', '<speak/>', date);
+    expect(ssml).toContain('X-RequestId:abc123\r\n');
+    expect(ssml).toContain('Content-Type:application/ssml+xml\r\n');
+    expect(ssml.endsWith('Path:ssml\r\n\r\n<speak/>')).toBe(true);
+    expect(edgeTextFramePath('X-RequestId:1\r\nContent-Type:application/json\r\nPath:turn.end\r\n\r\n{}')).toBe('turn.end');
+  });
+});
+
+describe('edge binary frames', () => {
+  it('splits the header (2-byte big-endian length) from the audio payload', () => {
+    const header = 'X-RequestId:1\r\nContent-Type:audio/mpeg\r\nX-StreamId:2\r\nPath:audio\r\n';
+    const payload = new Uint8Array([0xff, 0xfb, 0x90, 0x00]);
+    const frame = new Uint8Array(2 + header.length + payload.length);
+    frame[0] = header.length >> 8;
+    frame[1] = header.length & 0xff;
+    for (let i = 0; i < header.length; i++) frame[2 + i] = header.charCodeAt(i);
+    frame.set(payload, 2 + header.length);
+    const parsed = parseEdgeBinaryFrame(frame);
+    expect(parsed.path).toBe('audio');
+    expect([...parsed.payload]).toEqual([...payload]);
+  });
+  it('tolerates truncated frames', () => {
+    expect(parseEdgeBinaryFrame(new Uint8Array([0x00])).payload.byteLength).toBe(0);
+    expect(parseEdgeBinaryFrame(new Uint8Array([0x10, 0x00, 0x41])).path).toBe('');
+  });
+});
+
+describe('edge voices', () => {
+  it('picks Henri / Denise for French and falls back to French for unknown languages', () => {
+    expect(defaultEdgeVoice('fr-FR', 'male')).toBe('fr-FR-HenriNeural');
+    expect(defaultEdgeVoice('fr', 'female')).toBe('fr-FR-DeniseNeural');
+    expect(defaultEdgeVoice('en-GB', 'male')).toBe('en-US-AndrewMultilingualNeural');
+    expect(defaultEdgeVoice('xx', 'female')).toBe('fr-FR-DeniseNeural');
+  });
+  it('knows the gender of the common French voices', () => {
+    expect(edgeVoiceGender('fr-FR-HenriNeural')).toBe('male');
+    expect(edgeVoiceGender('fr-FR-RemyMultilingualNeural')).toBe('male');
+    expect(edgeVoiceGender('fr-FR-VivienneMultilingualNeural')).toBe('female');
+    expect(edgeVoiceGender('fr-CA-SylvieNeural')).toBe('female');
+    expect(edgeVoiceGender('zz-ZZ-NobodyNeural')).toBeUndefined();
+  });
+});

tests/voicePreference.test.ts

@@ -1,36 +1,61 @@
 import { describe, expect, it } from 'vitest';
-import { defaultOpenAiVoice, findLocalVoice, inferGender, rankSystemVoice, suggestedDownload } from '../src/lib/voicePreference';
-import type { VoiceModelStatus } from '../shared/voice';
+import { bestLocalUpgrade, defaultOpenAiVoice, findLocalVoice, inferGender, pickSpeaker, rankSystemVoice, resolveEdgeVoice, suggestedDownload } from '../src/lib/voicePreference';
+import type { VoiceModelStatus, VoiceSpeaker } from '../shared/voice';
 
-const model = (id: string, installed: boolean, speakers: Array<{ id: number; name: string; lang: string }>): VoiceModelStatus =>
-  ({ id, kind: 'tts', engine: 'piper', name: id, description: '', languages: ['fr'], sizeMb: 1, url: '', dir: id, files: [], speakers, installed, installedBytes: 0 }) as unknown as VoiceModelStatus;
+const model = (id: string, installed: boolean, speakers: VoiceSpeaker[], languages = ['fr']): VoiceModelStatus =>
+  ({ id, kind: 'tts', engine: 'piper', name: id, description: '', languages, sizeMb: 1, url: '', dir: id, files: [], speakers, installed, installedBytes: 0 }) as unknown as VoiceModelStatus;
 
 describe('inferGender', () => {
-  it('reads catalog labels, system voices and kokoro ids', () => {
+  it('reads catalog labels, system voices, kokoro ids and Edge short names', () => {
     expect(inferGender('Piper Tom (homme, français)')).toBe('male');
     expect(inferGender('Siwis (femme, français)')).toBe('female');
     expect(inferGender('Microsoft Paul - French (France)')).toBe('male');
     expect(inferGender('Microsoft Hortense - French (France)')).toBe('female');
     expect(inferGender('am_adam')).toBe('male');
+    expect(inferGender('fr-FR-HenriNeural')).toBe('male');
+    expect(inferGender('fr-FR-DeniseNeural')).toBe('female');
     expect(inferGender('Voix 3')).toBeUndefined();
   });
 });
 
 describe('local voice selection', () => {
+  const supertonic: VoiceSpeaker[] = [
+    { id: 6, name: 'Homme 2 (grave, posé)', lang: 'multi', gender: 'm' },
+    { id: 0, name: 'Femme 1', lang: 'multi', gender: 'f' }
+  ];
   const models = [
-    model('kokoro-v1', true, [{ id: 30, name: 'Siwis (femme, français)', lang: 'fr' }, { id: 4, name: 'Adam (homme, anglais US)', lang: 'en' }]),
+    model('kokoro-v1', true, [{ id: 30, name: 'Siwis (femme, français)', lang: 'fr' }, { id: 4, name: 'Adam (homme, anglais US)', lang: 'en' }], ['en', 'fr', 'multi']),
     model('piper-fr-tom', false, [{ id: 0, name: 'Tom', lang: 'fr' }]),
-    model('piper-fr-upmc', true, [{ id: 0, name: 'Jessica (femme)', lang: 'fr' }, { id: 1, name: 'Pierre (homme)', lang: 'fr' }])
+    model('piper-fr-upmc', true, [{ id: 0, name: 'Jessica (femme)', lang: 'fr' }, { id: 1, name: 'Pierre (homme)', lang: 'fr' }]),
+    model('supertonic-3', false, supertonic, ['fr', 'en', 'multi'])
   ];
   it('prefers an installed speaker of the wanted gender in the right language', () => {
     expect(findLocalVoice(models, 'fr-FR', 'male')).toEqual({ modelId: 'piper-fr-upmc', speaker: 1 });
     expect(findLocalVoice(models, 'fr-FR', 'female')).toEqual({ modelId: 'kokoro-v1', speaker: 30 });
     expect(findLocalVoice(models.slice(0, 2), 'fr', 'male')).toBeNull();
   });
-  it('suggests a French download when nothing matches', () => {
-    expect(suggestedDownload(models, 'fr', 'male')).toBe('piper-fr-tom');
+  it('ranks Supertonic above Kokoro and Piper once installed', () => {
+    const installed = models.map((m) => (m.id === 'supertonic-3' ? { ...m, installed: true } : m));
+    expect(findLocalVoice(installed, 'fr-FR', 'male')).toEqual({ modelId: 'supertonic-3', speaker: 6 });
+    expect(findLocalVoice(installed, 'fr-FR', 'female')).toEqual({ modelId: 'supertonic-3', speaker: 0 });
+  });
+  it('suggests Supertonic first, then the Piper voices, for a French download', () => {
+    expect(suggestedDownload(models, 'fr', 'male')).toBe('supertonic-3');
+    expect(suggestedDownload(models.filter((m) => m.id !== 'supertonic-3'), 'fr', 'male')).toBe('piper-fr-tom');
     expect(suggestedDownload(models, 'en', 'male')).toBeNull();
   });
+  it('reports the best local model still to download', () => {
+    expect(bestLocalUpgrade(models, 'fr-FR')).toBe('supertonic-3');
+    expect(bestLocalUpgrade(models.map((m) => ({ ...m, installed: true })), 'fr-FR')).toBeNull();
+  });
+  it('keeps the gender when switching models and falls back to the language', () => {
+    expect(pickSpeaker(models[3], 'fr-FR', 'male')).toBe(6);
+    expect(pickSpeaker(models[3], 'fr-FR', 'female')).toBe(0);
+    expect(pickSpeaker(models[2], 'fr', 'male')).toBe(1);
+    // Kokoro: no masculine French voice → the French voice, not an English one.
+    expect(pickSpeaker(models[0], 'fr', 'male')).toBe(30);
+    expect(pickSpeaker({ speakers: [] }, 'fr', 'male')).toBe(0);
+  });
 });
 
 describe('provider defaults', () => {
@@ -38,6 +63,12 @@ describe('provider defaults', () => {
     expect(defaultOpenAiVoice('male')).toBe('onyx');
     expect(defaultOpenAiVoice('female')).toBe('nova');
   });
+  it('keeps an explicit Edge voice only when it matches the gender', () => {
+    expect(resolveEdgeVoice('', 'fr-FR', 'male')).toBe('fr-FR-HenriNeural');
+    expect(resolveEdgeVoice('fr-FR-RemyMultilingualNeural', 'fr-FR', 'male')).toBe('fr-FR-RemyMultilingualNeural');
+    expect(resolveEdgeVoice('fr-FR-DeniseNeural', 'fr-FR', 'male')).toBe('fr-FR-HenriNeural');
+    expect(resolveEdgeVoice('fr-CH-ArianeNeural', 'fr-FR', 'female')).toBe('fr-CH-ArianeNeural');
+  });
   it('ranks system voices by language then gender', () => {
     const paul = { name: 'Microsoft Paul - French (France)', lang: 'fr-FR', localService: true };
     const hortense = { name: 'Microsoft Hortense - French (France)', lang: 'fr-FR', localService: true };