Files
EveFlow/electron/voice/ipc.ts
T
Claude 32551ccc0d 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
2026-09-04 15:37:00 +00:00

61 lines
3.9 KiB
TypeScript

import { ipcMain } from 'electron';
import { VOICE_IPC, type EdgeSynthesizeRequest, type KwsStartRequest, type SynthesizeRequest, type TranscribeRequest, type VadStartRequest } from '../../shared/voice';
import { edgeSynthesize, edgeVoices } from './edgeTts';
import { engineStatus, kwsFeed, kwsStart, kwsStop, synthesize, transcribe, unload, vadFeed, vadStart, vadStop } from './engine';
import { cancelDownload, downloadModel, listModels, removeModel } from './models';
export function registerVoiceIpc(): void {
ipcMain.handle(VOICE_IPC.status, () => engineStatus());
ipcMain.handle(VOICE_IPC.modelsList, () => listModels());
ipcMain.handle(VOICE_IPC.modelsDownload, (event, id: string) => downloadModel(id, event.sender));
ipcMain.handle(VOICE_IPC.modelsCancel, (_e, id: string) => {
cancelDownload(id);
return true;
});
ipcMain.handle(VOICE_IPC.modelsRemove, async (_e, id: string) => {
await unload(id).catch(() => undefined);
await removeModel(id);
return listModels();
});
ipcMain.handle(VOICE_IPC.transcribe, (_e, req: TranscribeRequest) => {
if (!req || !(req.wav instanceof Uint8Array) || req.wav.byteLength < 44 || req.wav.byteLength > 64 * 1024 * 1024) throw new Error('Audio invalide');
if (typeof req.modelId !== 'string') throw new Error('Modèle invalide');
return transcribe({ ...req, language: typeof req.language === 'string' ? req.language.slice(0, 8) : 'auto' });
});
ipcMain.handle(VOICE_IPC.synthesize, (_e, req: SynthesizeRequest) => {
if (!req || typeof req.text !== 'string' || !req.text.trim() || req.text.length > 5000) throw new Error('Texte invalide');
if (typeof req.modelId !== 'string') throw new Error('Modèle invalide');
return synthesize({
...req,
speaker: Number.isFinite(req.speaker) ? req.speaker : 0,
speed: Number.isFinite(req.speed) ? req.speed : 1,
language: typeof req.language === 'string' ? req.language.slice(0, 8) : undefined
});
});
ipcMain.handle(VOICE_IPC.edgeSynthesize, (_e, req: EdgeSynthesizeRequest) => {
if (!req || typeof req.text !== 'string' || !req.text.trim() || req.text.length > 5000) throw new Error('Texte invalide');
if (typeof req.voice !== 'string' || !/^[a-z]{2,3}-[A-Za-z]{2,4}-[A-Za-z0-9]+$/.test(req.voice)) throw new Error('Voix Edge invalide');
return edgeSynthesize({ text: req.text, voice: req.voice, speed: Number.isFinite(req.speed) ? req.speed : 1 });
});
ipcMain.handle(VOICE_IPC.edgeVoices, () => edgeVoices());
ipcMain.handle(VOICE_IPC.unload, (_e, id?: string) => unload(id));
ipcMain.handle(VOICE_IPC.kwsStart, (event, req: KwsStartRequest) => {
if (!req || !Array.isArray(req.keywords) || typeof req.modelId !== 'string') throw new Error('Requête invalide');
return kwsStart({ ...req, keywords: req.keywords.filter((k) => typeof k === 'string'), sensitivity: Number(req.sensitivity) || 3 }, event.sender);
});
ipcMain.handle(VOICE_IPC.kwsStop, () => kwsStop());
ipcMain.handle(VOICE_IPC.vadStart, (event, req: VadStartRequest) => {
if (!req || typeof req.modelId !== 'string') throw new Error('Requête invalide');
return vadStart({ modelId: req.modelId, silenceMs: Number(req.silenceMs) || 700, threshold: Number(req.threshold) || 0.5, maxUtteranceSec: Number(req.maxUtteranceSec) || 30 }, event.sender);
});
ipcMain.handle(VOICE_IPC.vadStop, () => vadStop());
ipcMain.on(VOICE_IPC.vadAudio, (_e, pcm: unknown, sampleRate: unknown) => {
if (!(pcm instanceof Uint8Array) || pcm.byteLength === 0 || pcm.byteLength > 1024 * 1024) return;
vadFeed(pcm, typeof sampleRate === 'number' && sampleRate > 0 ? sampleRate : 16000);
});
ipcMain.on(VOICE_IPC.kwsAudio, (_e, pcm: unknown, sampleRate: unknown) => {
if (!(pcm instanceof Uint8Array) || pcm.byteLength === 0 || pcm.byteLength > 1024 * 1024) return;
kwsFeed(pcm, typeof sampleRate === 'number' && sampleRate > 0 ? sampleRate : 16000);
});
}