diff --git a/README.md b/README.md index 0ba7729..508e7a2 100644 --- a/README.md +++ b/README.md @@ -1,7 +1,7 @@ # EveFlow 2 — Interface vocale JARVIS pour Hermes Agent [![Build](https://img.shields.io/github/actions/workflow/status/R0m1k3/EveFlow/windows-release.yml?style=flat-square)](https://github.com/R0m1k3/EveFlow/actions) -[![Version](https://img.shields.io/badge/version-2.4.1-brightgreen.svg?style=flat-square)](https://github.com/R0m1k3/EveFlow/releases) +[![Version](https://img.shields.io/badge/version-2.5.0-brightgreen.svg?style=flat-square)](https://github.com/R0m1k3/EveFlow/releases) [![License](https://img.shields.io/badge/license-MIT-lightgrey.svg?style=flat-square)](LICENSE) **EveFlow** est un compagnon de bureau Windows qui transforme [Hermes Agent](https://hermes-agent.nousresearch.com/) en assistant vocal à la JARVIS : un noyau holographique réactif au son, une conversation en streaming, les outils, sous-agents, approbations, crons, skills et sessions d'Hermes pilotés depuis un seul HUD. @@ -22,7 +22,7 @@ La version 2 est une réécriture complète : plus de robot 3D, un pipeline voca * **Capture micro** via AudioWorklet à 16 kHz, sans monitoring du micro dans les haut-parleurs, avec annulation d'écho et réduction de bruit. * **Détection d'activité vocale** (seuil adaptatif, sensibilité et silence de fin réglables) : l'enregistrement s'arrête tout seul quand vous avez fini de parler. * **Mains libres** : le micro se réactive après chaque réponse. -* **Modèles intégrés, hors ligne** (sherpa-onnx dans un processus séparé) : reconnaissance Whisper (base, small, large-v3 turbo) ou SenseVoice, synthèse Kokoro v1.0 (voix française Siwis et voix anglaises) ou Piper (Siwis, Tom, UPMC). Les modèles se téléchargent depuis **Paramètres → Modèles locaux** et tournent sur le processeur. +* **Modèles intégrés, hors ligne** (sherpa-onnx dans un processus séparé) : reconnaissance Parakeet v3, Whisper (base, small, large-v3 turbo) ou SenseVoice, synthèse **Supertonic 3** (31 langues dont le français, cinq voix masculines et cinq féminines, 44 kHz, 129 Mo, environ 7× plus rapide que le temps réel sur 4 cœurs), Kokoro v1.0 (excellent en anglais ; en français une seule voix féminine avec accent) ou Piper (Siwis, Tom, UPMC). Les modèles se téléchargent depuis **Paramètres → Modèles locaux** et tournent sur le processeur. * **Fin de phrase neuronale** : en écoute permanente, Silero VAD (0,6 Mo, sherpa-onnx) décide du début et de la fin de la commande à la place du seuil d'énergie ; moins de faux départs sur le bruit, coupure plus nette. Repli automatique sur le VAD énergétique si le modèle n'est pas installé. * **Vision d'écran** : « Jarvis, regarde mon écran » (ou le bouton de la barre de commande) joint une capture de l'écran principal à la question envoyée à Hermes. * **Actions locales instantanées** : « verrouille la session », « monte le son », « coupe le son », « piste suivante », « ouvre Spotify », « ouvre github.com »… exécutées sur le PC sans passer par Hermes, résultat lu à voix haute. Liste blanche d'actions dans le processus principal, désactivable dans les paramètres. @@ -30,13 +30,15 @@ La version 2 est une réécriture complète : plus de robot 3D, un pipeline voca * **Heures calmes et priorités** : plage horaire pendant laquelle les messages poussés s'affichent sans être lus ni faire clignoter le noyau (badge « non lus » à la place), thème nuit automatique, mots prioritaires lus quand même, résumé vocal des rapports longs (les premières phrases seulement). * **Mode mission** : un bouton dans la barre de commande bascule sur un second modèle Hermes (plus puissant) pour les tâches longues ; le modèle rapide reste utilisé pour la conversation courante. * **Widget compact « glanceable »** : état (veille, écoute, réflexion, parle), dernière phrase de l'assistant, badge de non-lus, indicateurs heures calmes et mission. -* **Voix JARVIS** : préréglage en un clic (Paramètres → Voix) : voix française masculine locale (Piper Tom, téléchargée automatiquement), timbre « JARVIS » (légèrement plus grave et posé, chaleur, présence, courte réverbération d'intercom), débit calme. Kokoro n'a pas de voix française masculine. +* **Voix Microsoft Edge** (moteur par défaut) : les voix neuronales de la lecture à voix haute d'Edge, gratuites, sans clé ni installation : Henri, Denise, Rémy, Vivienne, Éloise (fr-FR) et les voix fr-CA, fr-CH, fr-BE, plus de 300 voix dans 74 langues. Le rendu le plus naturel disponible ; nécessite une connexion. +* **Voix JARVIS** : deux préréglages en un clic (Paramètres → Voix) : en ligne (Edge Henri) ou hors ligne (Supertonic 3, voix masculine grave, téléchargé automatiquement), timbre « JARVIS » (légèrement plus grave et posé, chaleur, présence, courte réverbération d'intercom), débit calme. * **Reconnaissance française de référence** : Parakeet TDT 0.6B v3 (NVIDIA NeMo, 25 langues européennes) dans le catalogue, plus précis et bien plus rapide que Whisper sur processeur, avec ponctuation. Whisper base/small/turbo restent disponibles. -* **Voix masculine ou féminine** : un réglage unique (Paramètres → Voix) appliqué à tous les moteurs. En local, Piper Tom ou Pierre (UPMC) pour le masculin, téléchargé automatiquement si aucune voix masculine n'est installée ; onyx / nova pour les API compatibles OpenAI ; Paul / Hortense pour les voix Windows. +* **Voix masculine ou féminine** : un réglage unique (Paramètres → Voix) appliqué à tous les moteurs. Henri / Denise sur Edge ; en local Supertonic 3 (ou Piper Tom / Pierre) pour le masculin, téléchargé automatiquement si aucune voix masculine n'est installée, et le genre est conservé quand on change de modèle ; onyx / nova pour les API compatibles OpenAI ; Paul / Hortense pour les voix Windows. Google Translate n'a qu'une voix féminine par langue : le réglage l'indique. * **Barge-in** : en mains libres, parler par-dessus l'assistant coupe sa voix ; le seuil est relevé pendant qu'il parle pour ignorer l'écho du haut-parleur. * **Écoute permanente** : un détecteur de mot-clé de 3 Mo (sherpa-onnx, keyword spotting) tourne en continu sur le micro, quasi gratuit en CPU. « Jarvis » (ou n'importe quel mot-clé) ouvre l'écoute, « Jarvis, allume… » envoie directement la commande, et le mot coupe la voix en cours. Alternative : filtre du mot après transcription en mains libres. * **STT externe** : n'importe quelle API `/v1/audio/transcriptions` compatible OpenAI (Qwen3-ASR, Whisper, Speaches, faster-whisper-server, LocalAI, OpenAI). Repli sur la reconnaissance Chromium. -* **TTS externe** : API `/v1/audio/speech` compatible OpenAI, voix système Windows ou Google Translate. Lecture phrase par phrase pendant le streaming, préchargement du segment suivant, coupure instantanée. +* **TTS externe** : API `/v1/audio/speech` compatible OpenAI (Qwen3-TTS via un serveur compatible, Kokoro-FastAPI, OpenAI, LocalAI…), voix système Windows ou Google Translate. Lecture phrase par phrase pendant le streaming, préchargement du segment suivant, coupure instantanée. +* **Traitement du micro débrayable** : l'annulation d'écho, la réduction de bruit et le gain automatique de Chromium peuvent être coupés (Paramètres → Reconnaissance) ; avec un casque, le signal brut est souvent mieux transcrit. * Raccourcis globaux : `Ctrl+Shift+Espace` (micro), `Ctrl+Shift+J` (afficher/masquer), `Ctrl+Shift+Échap` (couper la voix). ### Hermes, toute la puissance diff --git a/docs/ROADMAP.md b/docs/ROADMAP.md index c51f7c0..9a94776 100644 --- a/docs/ROADMAP.md +++ b/docs/ROADMAP.md @@ -8,7 +8,8 @@ |---|---|---| | HUD arc-reactor réactif au son | Fait | Canvas 2D optimisé (pas d'ombres, couleurs en cache, 30 fps en veille, arrêt fenêtre masquée) | | Reconnaissance vocale locale | Fait | Whisper base/small/turbo via sherpa-onnx dans un processus utilitaire | -| Synthèse vocale locale | Fait | Kokoro v1.0 (voix française Siwis) et Piper fr | +| Synthèse vocale locale | Fait (2.5.0) | Supertonic 3 (31 langues, 5 voix masculines + 5 féminines, 44 kHz), Kokoro v1.0 (anglais ; français féminin avec accent) et Piper fr | +| Synthèse vocale en ligne | Fait (2.5.0) | Voix neuronales Microsoft Edge (Henri, Denise, Rémy, Vivienne…), gratuites, sans clé, via WebSocket signé dans le processus principal | | Mot d'activation permanent | Fait (2.2.0) | Keyword spotting sherpa-onnx en continu ; mot-clé libre encodé en BPE ; validé sur audio réel (détection, zéro faux positif sur le test anglais) | | Mot d'activation après transcription | Fait | Filtre « Jarvis … » en mains libres, tolérant aux erreurs de transcription | | Détection de fin de phrase | Fait (2.3.0) | Silero VAD neuronal dans le worker (segment renvoyé au renderer), repli sur le VAD énergétique si le modèle manque | @@ -83,6 +84,8 @@ Sources : [jarvis-desktop-ai](https://github.com/ccarloshenri/jarvis-desktop-ai) | Correctifs 2.4.0.1 | réponse vide en chat completions désormais expliquée (JSON non streamé ou erreur HTTP 200), la liaison ne passe plus en « dégradé » quand seule l'API des crons échoue, transcriptions parasites (« (cliquant) », « *Claire* ») ignorées, préférence de voix masculine/féminine | | Parakeet v3 vs Whisper base sur trois phrases Piper (fr) (2.4.1) | Parakeet : 3/3 exactes avec ponctuation, 0,4 à 0,5 s à chaud (6,7 s au premier appel) ; Whisper base : erreurs sur « Jarvis », « Peux-tu », 0,7 à 0,9 s | | Worklets audio sous CSP stricte (2.4.1) | chargement des modules statiques OK dans l'application empaquetée | +| Voix françaises (2.5.0) | Edge Henri : MP3 reçu de bout en bout (32 ko pour 4 s). Supertonic 3 en français : 10 voix, RTF 0,14 sur 4 cœurs (8,7 s d'audio en 1,3 s), genres déterminés par mesure de la fréquence fondamentale (voix 0-4 : 170-210 Hz, voix 5-9 : 92-137 Hz) ; le worker compilé accepte `language` et bascule sur l'anglais pour une langue inconnue | +| Reconnaissance française : Parakeet v3 vs Qwen3-ASR 0.6B int8 (2.5.0) | Six phrases Supertonic (3,8 s) : Parakeet WER 8,5 % (erreurs surtout de forme : « 14h30 »), 384 ms par phrase ; Qwen3-ASR WER 15,3 % (« mémoires vivres »), 1 477 ms, 940 Mo. Qwen3-ASR n'est pas ajouté au catalogue | | Serveur MCP (2.4.0) | initialize, tools/list (14 outils), tools/call côté principal (presse-papiers, capture image) et côté renderer (état, message dans le fil) | Sur un PC à 28 cœurs les temps sont nettement plus courts. Whisper small est maintenant recommandé pour le français. diff --git a/electron/preload.ts b/electron/preload.ts index 94b6dad..83e52f0 100644 --- a/electron/preload.ts +++ b/electron/preload.ts @@ -15,7 +15,7 @@ import { } from '../shared/ipc'; import type { EveFlowBridge, SystemAction, SystemActionResult, Unsubscribe } from '../shared/bridge'; import type { McpToolRequest, McpToolResponse } from '../shared/ipc'; -import { VOICE_IPC, type KwsDetection, type KwsStartRequest, type VadEvent, type VadStartRequest, type SynthesizeRequest, type SynthesizeResult, type TranscribeRequest, type TranscribeResult, type VoiceDownloadProgress, type VoiceEngineStatus, type VoiceModelStatus } from '../shared/voice'; +import { VOICE_IPC, type EdgeSynthesizeRequest, type EdgeSynthesizeResult, type EdgeVoice, type KwsDetection, type KwsStartRequest, type VadEvent, type VadStartRequest, type SynthesizeRequest, type SynthesizeResult, type TranscribeRequest, type TranscribeResult, type VoiceDownloadProgress, type VoiceEngineStatus, type VoiceModelStatus } from '../shared/voice'; function subscribe(channel: string, callback: (payload: T) => void): Unsubscribe { const listener = (_event: Electron.IpcRendererEvent, payload: T) => callback(payload); @@ -74,6 +74,8 @@ const api: EveFlowBridge = { onProgress: (cb: (progress: VoiceDownloadProgress) => void) => subscribe(VOICE_IPC.modelsProgress, cb), transcribe: (req: TranscribeRequest) => ipcRenderer.invoke(VOICE_IPC.transcribe, req) as Promise, synthesize: (req: SynthesizeRequest) => ipcRenderer.invoke(VOICE_IPC.synthesize, req) as Promise, + edgeSynthesize: (req: EdgeSynthesizeRequest) => ipcRenderer.invoke(VOICE_IPC.edgeSynthesize, req) as Promise, + edgeVoices: () => ipcRenderer.invoke(VOICE_IPC.edgeVoices) as Promise, unload: (id?: string) => ipcRenderer.invoke(VOICE_IPC.unload, id) as Promise, kwsStart: (req: KwsStartRequest) => ipcRenderer.invoke(VOICE_IPC.kwsStart, req) as Promise<{ accepted: string[]; rejected: string[] }>, kwsStop: () => ipcRenderer.invoke(VOICE_IPC.kwsStop) as Promise, diff --git a/electron/voice/catalog.ts b/electron/voice/catalog.ts index 39efb7a..ee91d5d 100644 --- a/electron/voice/catalog.ts +++ b/electron/voice/catalog.ts @@ -17,6 +17,22 @@ const KOKORO_SPEAKERS: VoiceSpeaker[] = [ { id: 26, name: 'George (homme, anglais UK)', lang: 'en' } ]; +// Supertonic 3 ships ten voice styles in voice.bin (five feminine, five masculine). The ordering +// was checked by measuring the fundamental frequency of French synthesis: sid 0-4 around +// 170-210 Hz, sid 5-9 around 90-140 Hz. +const SUPERTONIC_SPEAKERS: VoiceSpeaker[] = [ + { id: 6, name: 'Homme 2 (grave, posé)', lang: 'multi', gender: 'm' }, + { id: 9, name: 'Homme 5 (grave)', lang: 'multi', gender: 'm' }, + { id: 7, name: 'Homme 3', lang: 'multi', gender: 'm' }, + { id: 8, name: 'Homme 4', lang: 'multi', gender: 'm' }, + { id: 5, name: 'Homme 1 (clair)', lang: 'multi', gender: 'm' }, + { id: 0, name: 'Femme 1', lang: 'multi', gender: 'f' }, + { id: 1, name: 'Femme 2', lang: 'multi', gender: 'f' }, + { id: 2, name: 'Femme 3', lang: 'multi', gender: 'f' }, + { id: 3, name: 'Femme 4', lang: 'multi', gender: 'f' }, + { id: 4, name: 'Femme 5', lang: 'multi', gender: 'f' } +]; + export const VOICE_CATALOG: VoiceModelSpec[] = [ { id: 'whisper-base', @@ -112,20 +128,36 @@ export const VOICE_CATALOG: VoiceModelSpec[] = [ files: ['silero_vad.onnx'], recommended: true }, + { + id: 'supertonic-3', + kind: 'tts', + engine: 'supertonic', + name: 'Supertonic 3 (31 langues, 5 voix masculines et 5 féminines)', + description: + 'La meilleure voix française locale : naturelle, sans accent, dix voix au choix, 44 kHz. Environ 7 fois plus rapide que le temps réel sur 4 cœurs, 100 M de paramètres.', + languages: ['fr', 'en', 'de', 'es', 'it', 'pt', 'multi'], + sizeMb: 129, + url: `${TTS}/sherpa-onnx-supertonic-3-tts-int8-2026-05-11.tar.bz2`, + dir: 'sherpa-onnx-supertonic-3-tts-int8-2026-05-11', + files: ['duration_predictor.int8.onnx', 'text_encoder.int8.onnx', 'vector_estimator.int8.onnx', 'vocoder.int8.onnx', 'tts.json', 'unicode_indexer.bin', 'voice.bin'], + speakers: SUPERTONIC_SPEAKERS, + sampleRate: 44100, + recommended: true + }, { id: 'kokoro-v1', kind: 'tts', engine: 'kokoro', name: 'Kokoro v1.0 multilingue', - description: 'Voix très naturelle, une voix française (Siwis) et de nombreuses voix anglaises. 24 kHz.', - languages: ['fr', 'en', 'multi'], + description: + 'Excellent en anglais (nombreuses voix). En français : une seule voix, féminine (Siwis), avec un accent marqué (phonémisation espeak). Préférez Supertonic 3 pour le français. 24 kHz.', + languages: ['en', 'fr', 'multi'], sizeMb: 349, url: `${TTS}/kokoro-multi-lang-v1_0.tar.bz2`, dir: 'kokoro-multi-lang-v1_0', files: ['model.onnx', 'voices.bin', 'tokens.txt', 'lexicon-us-en.txt', 'lexicon-zh.txt', 'espeak-ng-data/phontab'], speakers: KOKORO_SPEAKERS, - sampleRate: 24000, - recommended: true + sampleRate: 24000 }, { id: 'piper-fr-siwis', @@ -181,6 +213,9 @@ export function findModel(id: string): VoiceModelSpec | undefined { // Speaker gender from the label ("(homme, …)", "(femme, …)", known first names) so the UI and the // voice preference can pick a masculine or feminine voice without a lookup table per model. const MALE = /\b(homme|tom|pierre|adam|michael|eric|liam|george|lewis|daniel|fenrir|puck|onyx|echo|santa)\b/i; + +/** Languages accepted by the Supertonic 3 text front-end (2-letter codes). */ +export const SUPERTONIC_LANGS = new Set(['ar', 'bg', 'hr', 'cs', 'da', 'nl', 'en', 'et', 'fi', 'fr', 'de', 'el', 'hi', 'hu', 'id', 'it', 'ja', 'ko', 'lv', 'lt', 'pl', 'pt', 'ro', 'ru', 'sk', 'sl', 'es', 'sv', 'tr', 'uk', 'vi']); for (const spec of VOICE_CATALOG) { for (const sp of spec.speakers ?? []) { if (!sp.gender) sp.gender = /\b(femme|female)\b/i.test(sp.name) ? 'f' : MALE.test(sp.name) ? 'm' : /\bfemme\b/i.test(spec.name) ? 'f' : /\bhomme\b/i.test(spec.name) ? 'm' : undefined; diff --git a/electron/voice/edgeTts.ts b/electron/voice/edgeTts.ts new file mode 100644 index 0000000..a0399b8 --- /dev/null +++ b/electron/voice/edgeTts.ts @@ -0,0 +1,146 @@ +/** + * Microsoft Edge "Read aloud" neural voices (the service behind the Edge browser's read-aloud + * feature): free, no key, very natural French voices with a real masculine/feminine choice + * (Henri, Denise, Rémy, Vivienne…). Runs in the main process: one WebSocket per sentence, + * MP3 back to the renderer. + */ +import { createHash, randomBytes, randomUUID } from 'node:crypto'; +import type { EdgeSynthesizeRequest, EdgeSynthesizeResult, EdgeVoice } from '../../shared/voice'; +import { + EDGE_CHROMIUM_VERSION, + EDGE_VOICES_URL, + EDGE_WSS_URL, + edgeConfigMessage, + edgeConnectionId, + edgeHeaders, + edgeSsml, + edgeSsmlMessage, + edgeTextFramePath, + edgeTokenInput, + parseEdgeBinaryFrame +} from '../../shared/edgeTts'; +import { log } from '../logger'; + +/** Seconds to add to the local clock so the signed token matches the server's time window. */ +let clockSkewSec = 0; +let voicesCache: { at: number; voices: EdgeVoice[] } | null = null; +const VOICES_TTL_MS = 6 * 60 * 60 * 1000; +const SYNTH_TIMEOUT_MS = 20_000; + +function token(): string { + return createHash('sha256').update(edgeTokenInput(Date.now(), clockSkewSec), 'ascii').digest('hex').toUpperCase(); +} + +function signedUrl(): string { + return `${EDGE_WSS_URL}&ConnectionId=${edgeConnectionId(randomUUID())}&Sec-MS-GEC=${token()}&Sec-MS-GEC-Version=1-${EDGE_CHROMIUM_VERSION}`; +} + +function headers(): Record { + return { ...edgeHeaders(), Cookie: `muid=${randomBytes(16).toString('hex')};` }; +} + +/** Learn the server clock from a plain HTTPS response (the WebSocket handshake hides its headers). */ +async function syncClock(): Promise { + try { + const res = await fetch(EDGE_VOICES_URL, { method: 'HEAD', headers: headers() }); + const date = res.headers.get('date'); + if (!date) return; + const server = Date.parse(date); + if (Number.isFinite(server)) { + clockSkewSec = (server - Date.now()) / 1000; + log('INFO', 'edge-tts', `clock skew ${clockSkewSec.toFixed(0)} s`); + } + } catch (err) { + log('WARN', 'edge-tts', `clock sync failed: ${(err as Error).message}`); + } +} + +function synthesizeOnce(req: EdgeSynthesizeRequest): Promise { + return new Promise((resolve, reject) => { + const chunks: Uint8Array[] = []; + let settled = false; + let ws: WebSocket; + try { + // Node's global WebSocket accepts extra handshake headers (undici), which the service checks. + ws = new (WebSocket as unknown as new (url: string, options: { headers: Record }) => WebSocket)(signedUrl(), { headers: headers() }); + } catch (err) { + reject(err as Error); + return; + } + ws.binaryType = 'arraybuffer'; + const finish = (err?: Error) => { + if (settled) return; + settled = true; + clearTimeout(timer); + try { + ws.close(); + } catch { + /* already closed */ + } + if (err) reject(err); + else { + const total = chunks.reduce((n, c) => n + c.byteLength, 0); + const out = new Uint8Array(total); + let o = 0; + for (const c of chunks) { + out.set(c, o); + o += c.byteLength; + } + resolve(out); + } + }; + const timer = setTimeout(() => finish(new Error('Edge TTS : délai dépassé')), SYNTH_TIMEOUT_MS); + ws.onopen = () => { + ws.send(edgeConfigMessage()); + ws.send(edgeSsmlMessage(edgeConnectionId(randomUUID()), edgeSsml(req.text, req.voice, req.speed))); + }; + ws.onmessage = (event: MessageEvent) => { + if (typeof event.data === 'string') { + if (edgeTextFramePath(event.data) === 'turn.end') finish(); + return; + } + const frame = new Uint8Array(event.data as ArrayBuffer); + const { path, payload } = parseEdgeBinaryFrame(frame); + if (path === 'audio' && payload.byteLength) chunks.push(payload); + }; + ws.onerror = (event: Event) => finish(new Error(`Edge TTS : connexion refusée (${(event as { message?: string }).message ?? 'erreur réseau'})`)); + ws.onclose = (event: CloseEvent) => { + if (!settled) finish(chunks.length ? undefined : new Error(`Edge TTS : connexion fermée (${event.code}${event.reason ? ' ' + event.reason : ''})`)); + }; + }); +} + +export async function edgeSynthesize(req: EdgeSynthesizeRequest): Promise { + const started = Date.now(); + let mp3: Uint8Array; + try { + mp3 = await synthesizeOnce(req); + } catch (err) { + // A refused handshake is almost always a stale signature: resync the clock and retry once. + log('WARN', 'edge-tts', `first attempt failed (${(err as Error).message}), resyncing clock`); + await syncClock(); + mp3 = await synthesizeOnce(req); + } + if (!mp3.byteLength) throw new Error('Edge TTS : aucun audio reçu'); + return { mp3, durationMs: Date.now() - started }; +} + +/** Voice list from the service (cached six hours); falls back to an empty list offline. */ +export async function edgeVoices(): Promise { + if (voicesCache && Date.now() - voicesCache.at < VOICES_TTL_MS) return voicesCache.voices; + const url = `${EDGE_VOICES_URL}&Sec-MS-GEC=${token()}&Sec-MS-GEC-Version=1-${EDGE_CHROMIUM_VERSION}`; + const res = await fetch(url, { headers: headers() }); + if (!res.ok) throw new Error(`Edge TTS : liste des voix HTTP ${res.status}`); + const raw = (await res.json()) as Array<{ ShortName?: string; FriendlyName?: string; Locale?: string; Gender?: string }>; + const voices: EdgeVoice[] = raw + .filter((v) => typeof v.ShortName === 'string' && typeof v.Locale === 'string') + .map((v) => ({ + shortName: v.ShortName!, + name: v.ShortName!.split('-')[2]?.replace(/(Multilingual)?Neural$/, '') || v.FriendlyName || v.ShortName!, + locale: v.Locale!, + gender: v.Gender === 'Male' ? ('m' as const) : ('f' as const) + })) + .sort((a, b) => a.locale.localeCompare(b.locale) || a.name.localeCompare(b.name)); + voicesCache = { at: Date.now(), voices }; + return voices; +} diff --git a/electron/voice/engine.ts b/electron/voice/engine.ts index c880963..0987783 100644 --- a/electron/voice/engine.ts +++ b/electron/voice/engine.ts @@ -134,7 +134,7 @@ export function transcribe(req: TranscribeRequest): Promise { export async function synthesize(req: SynthesizeRequest): Promise { const result = await request & { wav: string }>( - { type: 'synthesize', model: modelRef(req.modelId), text: req.text, speaker: req.speaker, speed: req.speed }, + { type: 'synthesize', model: modelRef(req.modelId), text: req.text, speaker: req.speaker, speed: req.speed, language: req.language }, 180_000 ); const buffer = Buffer.from(result.wav, 'base64'); diff --git a/electron/voice/ipc.ts b/electron/voice/ipc.ts index 831871a..161ca10 100644 --- a/electron/voice/ipc.ts +++ b/electron/voice/ipc.ts @@ -1,5 +1,6 @@ import { ipcMain } from 'electron'; -import { VOICE_IPC, type KwsStartRequest, type SynthesizeRequest, type TranscribeRequest, type VadStartRequest } from '../../shared/voice'; +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'; @@ -24,8 +25,19 @@ export function registerVoiceIpc(): void { 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 }); + 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'); diff --git a/electron/voice/worker.ts b/electron/voice/worker.ts index c14ebf9..0ce113e 100644 --- a/electron/voice/worker.ts +++ b/electron/voice/worker.ts @@ -6,6 +6,7 @@ import os from 'node:os'; import path from 'node:path'; import type { VoiceEngineKind } from '../../shared/voice'; +import { SUPERTONIC_LANGS } from './catalog'; interface ModelRef { id: string; @@ -17,7 +18,7 @@ interface ModelRef { type Request = | { id: number; type: 'status' } | { id: number; type: 'transcribe'; model: ModelRef; wav: Uint8Array | string; language: string } - | { id: number; type: 'synthesize'; model: ModelRef; text: string; speaker: number; speed: number } + | { id: number; type: 'synthesize'; model: ModelRef; text: string; speaker: number; speed: number; language?: string } | { id: number; type: 'unload'; modelId?: string } | { id: number; type: 'kws.start'; model: ModelRef; keywordsFile: string; threshold: number; score: number } | { id: number; type: 'kws.audio'; pcm: string; sampleRate: number } @@ -55,8 +56,10 @@ type Sherpa = { OfflineTts: new (config: unknown) => { numSpeakers: number; sampleRate: number; - generate: (req: { text: string; sid: number; speed: number; enableExternalBuffer?: boolean }) => { samples: Float32Array; sampleRate: number }; + generate: (req: { text: string; sid: number; speed: number; enableExternalBuffer?: boolean; generationConfig?: unknown }) => { samples: Float32Array; sampleRate: number }; }; + /** Per-request options for the newer engines (Supertonic reads `extra.lang`). */ + GenerationConfig: new (opts: { sid: number; speed: number; numSteps?: number; extra?: Record }) => unknown; version: string; }; @@ -152,6 +155,19 @@ function getSynthesizer(model: ModelRef) { ttsModel = { vits: { model: p(onnx), tokens: p('tokens.txt'), dataDir: p('espeak-ng-data') } }; break; } + case 'supertonic': + ttsModel = { + supertonic: { + durationPredictor: p('duration_predictor.int8.onnx'), + textEncoder: p('text_encoder.int8.onnx'), + vectorEstimator: p('vector_estimator.int8.onnx'), + vocoder: p('vocoder.int8.onnx'), + ttsJson: p('tts.json'), + unicodeIndexer: p('unicode_indexer.bin'), + voiceStyle: p('voice.bin') + } + }; + break; default: throw new Error(`Moteur TTS non supporté : ${model.engine}`); } @@ -160,6 +176,12 @@ function getSynthesizer(model: ModelRef) { return tts; } +/** 2-letter code accepted by Supertonic 3 ("fr-FR" → "fr"); English when unknown, as upstream does. */ +function supertonicLang(language: string | undefined): string { + const code = (language ?? '').toLowerCase().split(/[-_]/)[0]; + return SUPERTONIC_LANGS.has(code) ? code : 'en'; +} + // ── audio helpers ────────────────────────────────────────────────────────── function decodeWav(bytes: Uint8Array): { samples: Float32Array; sampleRate: number } { const view = new DataView(bytes.buffer, bytes.byteOffset, bytes.byteLength); @@ -397,8 +419,19 @@ function handle(req: Request): unknown { const started = Date.now(); const tts = getSynthesizer(req.model); const sid = Math.max(0, Math.min(tts.numSpeakers - 1, Math.floor(req.speaker))); + const speed = Math.max(0.5, Math.min(2, req.speed || 1)); // Electron forbids N-API external buffers: ask sherpa-onnx to copy the samples into a V8 buffer. - const audio = tts.generate({ text: req.text, sid, speed: Math.max(0.5, Math.min(2, req.speed || 1)), enableExternalBuffer: false }); + const audio = + req.model.engine === 'supertonic' + ? tts.generate({ + text: req.text, + sid, + speed, + enableExternalBuffer: false, + // Supertonic needs the language of the text; 5 denoising steps is the quality/speed sweet spot. + generationConfig: new (loadSherpa().GenerationConfig)({ sid, speed, numSteps: 5, extra: { lang: supertonicLang(req.language) } }) + }) + : tts.generate({ text: req.text, sid, speed, enableExternalBuffer: false }); const wav = encodeWav(audio.samples, audio.sampleRate); return { wav: Buffer.from(wav.buffer, wav.byteOffset, wav.byteLength).toString('base64'), diff --git a/package.json b/package.json index da1d289..5da9837 100644 --- a/package.json +++ b/package.json @@ -1,7 +1,7 @@ { "name": "eveflow", - "version": "2.4.1", - "releaseVersion": "2.4.1", + "version": "2.5.0", + "releaseVersion": "2.5.0", "description": "JARVIS-style desktop HUD for Hermes Agent: voice, streaming runs, scheduled jobs, skills and telemetry", "main": "dist-electron/main.js", "private": true, diff --git a/shared/bridge.ts b/shared/bridge.ts index ebc5c71..5cc2208 100644 --- a/shared/bridge.ts +++ b/shared/bridge.ts @@ -13,6 +13,9 @@ import type { } from './ipc'; import type { McpToolRequest, McpToolResponse } from './ipc'; import type { + EdgeSynthesizeRequest, + EdgeSynthesizeResult, + EdgeVoice, KwsDetection, KwsStartRequest, VadEvent, @@ -75,6 +78,9 @@ export interface EveFlowBridge { onProgress: (cb: (progress: VoiceDownloadProgress) => void) => Unsubscribe; transcribe: (req: TranscribeRequest) => Promise; synthesize: (req: SynthesizeRequest) => Promise; + /** Microsoft Edge neural voices (online, free): MP3 for one sentence. */ + edgeSynthesize: (req: EdgeSynthesizeRequest) => Promise; + edgeVoices: () => Promise; unload: (id?: string) => Promise; kwsStart: (req: KwsStartRequest) => Promise<{ accepted: string[]; rejected: string[] }>; kwsStop: () => Promise; diff --git a/shared/edgeTts.ts b/shared/edgeTts.ts new file mode 100644 index 0000000..4359ceb --- /dev/null +++ b/shared/edgeTts.ts @@ -0,0 +1,119 @@ +/** + * Pure helpers for the Microsoft Edge "Read aloud" speech service (the endpoint used by the + * Edge browser, no API key): request signing input, SSML building, frame parsing and the + * default French voices. No Node or DOM dependency so it is shared by main and tests. + */ + +export const EDGE_TRUSTED_CLIENT_TOKEN = '6A5AA1D4EAFF4E9FB37E23D68491D6F4'; +export const EDGE_CHROMIUM_VERSION = '143.0.3650.75'; +export const EDGE_WSS_URL = `wss://speech.platform.bing.com/consumer/speech/synthesize/readaloud/edge/v1?TrustedClientToken=${EDGE_TRUSTED_CLIENT_TOKEN}`; +export const EDGE_VOICES_URL = `https://speech.platform.bing.com/consumer/speech/synthesize/readaloud/voices/list?trustedclienttoken=${EDGE_TRUSTED_CLIENT_TOKEN}`; +export const EDGE_OUTPUT_FORMAT = 'audio-24khz-48kbitrate-mono-mp3'; + +const WIN_EPOCH_SEC = 11644473600; + +/** + * String whose SHA-256 (upper-case hex) is the `Sec-MS-GEC` value: Windows file time (100 ns + * ticks since 1601) rounded down to 5 minutes, followed by the trusted client token. + * `nowMs` is the client clock, `skewSec` the correction learned from the server's Date header. + */ +export function edgeTokenInput(nowMs: number, skewSec = 0): string { + let seconds = Math.floor(nowMs / 1000 + skewSec) + WIN_EPOCH_SEC; + seconds -= seconds % 300; + // 10 million ticks per second; BigInt keeps the 18-digit value exact. + const ticks = BigInt(seconds) * 10_000_000n; + return `${ticks}${EDGE_TRUSTED_CLIENT_TOKEN}`; +} + +export function edgeHeaders(): Record { + const major = EDGE_CHROMIUM_VERSION.split('.')[0]; + return { + 'User-Agent': `Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/${major}.0.0.0 Safari/537.36 Edg/${major}.0.0.0`, + 'Accept-Language': 'en-US,en;q=0.9', + Pragma: 'no-cache', + 'Cache-Control': 'no-cache', + Origin: 'chrome-extension://jdiccldimpdaibmpdkjnbmckianbfold' + }; +} + +export function escapeXml(text: string): string { + return text.replace(/&/g, '&').replace(//g, '>').replace(/"/g, '"').replace(/'/g, '''); +} + +/** Prosody rate attribute for a playback speed multiplier (1 = "+0%", 1.25 = "+25%"). */ +export function edgeRate(speed: number): string { + const pct = Math.round((Math.max(0.5, Math.min(2, speed || 1)) - 1) * 100); + return `${pct >= 0 ? '+' : ''}${pct}%`; +} + +export function edgeSsml(text: string, voice: string, speed: number): string { + const lang = voice.split('-').slice(0, 2).join('-') || 'fr-FR'; + return ( + `` + + `${escapeXml(text)}` + ); +} + +/** Timestamp header the service expects ("JavaScript date string"). */ +export function edgeTimestamp(date = new Date()): string { + return date.toUTCString().replace('GMT', 'GMT+0000 (Coordinated Universal Time)'); +} + +export function edgeConfigMessage(date = new Date()): string { + return ( + `X-Timestamp:${edgeTimestamp(date)}\r\nContent-Type:application/json; charset=utf-8\r\nPath:speech.config\r\n\r\n` + + `{"context":{"synthesis":{"audio":{"metadataoptions":{"sentenceBoundaryEnabled":"false","wordBoundaryEnabled":"false"},"outputFormat":"${EDGE_OUTPUT_FORMAT}"}}}}` + ); +} + +export function edgeSsmlMessage(requestId: string, ssml: string, date = new Date()): string { + return `X-RequestId:${requestId}\r\nContent-Type:application/ssml+xml\r\nX-Timestamp:${edgeTimestamp(date)}Z\r\nPath:ssml\r\n\r\n${ssml}`; +} + +/** Split a binary frame into its text headers and payload (2-byte big-endian header length). */ +export function parseEdgeBinaryFrame(frame: Uint8Array): { path: string; payload: Uint8Array } { + if (frame.byteLength < 2) return { path: '', payload: new Uint8Array(0) }; + const headerLength = (frame[0] << 8) | frame[1]; + const end = Math.min(frame.byteLength, 2 + headerLength); + let header = ''; + for (let i = 2; i < end; i++) header += String.fromCharCode(frame[i]); + const path = /Path:\s*([^\r\n]+)/i.exec(header)?.[1]?.trim() ?? ''; + return { path, payload: frame.subarray(end) }; +} + +/** Path of a text frame ("turn.start", "response", "audio.metadata", "turn.end"). */ +export function edgeTextFramePath(message: string): string { + return /Path:\s*([^\r\n]+)/i.exec(message)?.[1]?.trim() ?? ''; +} + +export function edgeConnectionId(hex32: string): string { + return hex32.replace(/-/g, '').toLowerCase(); +} + +/** Well-known voices per language so the choice works before the voice list is fetched. */ +export const EDGE_DEFAULT_VOICES: Record = { + fr: { male: 'fr-FR-HenriNeural', female: 'fr-FR-DeniseNeural' }, + en: { male: 'en-US-AndrewMultilingualNeural', female: 'en-US-AvaMultilingualNeural' }, + de: { male: 'de-DE-ConradNeural', female: 'de-DE-KatjaNeural' }, + es: { male: 'es-ES-AlvaroNeural', female: 'es-ES-ElviraNeural' }, + it: { male: 'it-IT-DiegoNeural', female: 'it-IT-ElsaNeural' }, + pt: { male: 'pt-BR-AntonioNeural', female: 'pt-BR-FranciscaNeural' } +}; + +/** Default Edge voice for a language ("fr-FR", "fr", "en-GB") and gender; French when unknown. */ +export function defaultEdgeVoice(language: string, gender: 'male' | 'female'): string { + const lang = (language || 'fr').toLowerCase().split(/[-_]/)[0]; + return (EDGE_DEFAULT_VOICES[lang] ?? EDGE_DEFAULT_VOICES.fr)[gender]; +} + +/** Gender of an Edge voice from its short name, using the built-in table then common first names. */ +export function edgeVoiceGender(shortName: string): 'male' | 'female' | undefined { + for (const pair of Object.values(EDGE_DEFAULT_VOICES)) { + if (pair.male === shortName) return 'male'; + if (pair.female === shortName) return 'female'; + } + const name = shortName.split('-')[2]?.replace(/(Multilingual)?Neural$/i, '') ?? ''; + if (/^(Henri|Remy|Rémy|Gerard|Antoine|Jean|Thierry|Fabrice|Claude|Andrew|Brian|Guy|Christopher|Eric|Roger|Steffan|Ryan|Thomas|Conrad|Alvaro|Diego|Antonio)$/i.test(name)) return 'male'; + if (/^(Denise|Eloise|Vivienne|Charline|Sylvie|Ariane|Ava|Emma|Jenny|Aria|Michelle|Ana|Sonia|Libby|Katja|Elvira|Elsa|Francisca)$/i.test(name)) return 'female'; + return undefined; +} diff --git a/shared/voice.ts b/shared/voice.ts index a17ac4e..b3975a7 100644 --- a/shared/voice.ts +++ b/shared/voice.ts @@ -1,7 +1,7 @@ /** Local voice engine contract (sherpa-onnx in a utility process). Shared by main and renderer. */ export type VoiceModelKind = 'stt' | 'tts' | 'kws' | 'vad'; -export type VoiceEngineKind = 'whisper' | 'sense-voice' | 'nemo-transducer' | 'kokoro' | 'piper' | 'kws-transducer' | 'silero'; +export type VoiceEngineKind = 'whisper' | 'sense-voice' | 'nemo-transducer' | 'kokoro' | 'piper' | 'supertonic' | 'kws-transducer' | 'silero'; export interface VoiceSpeaker { id: number; @@ -62,6 +62,31 @@ export interface SynthesizeRequest { text: string; speaker: number; speed: number; + /** BCP-47 tag or 2-letter code of the text (multilingual engines such as Supertonic need it). */ + language?: string; +} + +/** Microsoft Edge "Read aloud" neural voices (online, no key). */ +export interface EdgeVoice { + /** e.g. fr-FR-HenriNeural */ + shortName: string; + /** Display name, e.g. Henri */ + name: string; + locale: string; + gender: 'm' | 'f'; +} + +export interface EdgeSynthesizeRequest { + text: string; + voice: string; + /** Playback speed multiplier (0.5 .. 2). */ + speed: number; +} + +export interface EdgeSynthesizeResult { + /** MP3, 24 kHz mono 48 kbit/s. */ + mp3: Uint8Array; + durationMs: number; } export interface SynthesizeResult { @@ -115,6 +140,8 @@ export const VOICE_IPC = { modelsProgress: 'voice:models:progress', transcribe: 'voice:transcribe', synthesize: 'voice:synthesize', + edgeSynthesize: 'voice:edge:synthesize', + edgeVoices: 'voice:edge:voices', unload: 'voice:unload', kwsStart: 'voice:kws:start', kwsStop: 'voice:kws:stop', diff --git a/src/components/settings/ModelsSection.tsx b/src/components/settings/ModelsSection.tsx index 9c38e31..d2d813b 100644 --- a/src/components/settings/ModelsSection.tsx +++ b/src/components/settings/ModelsSection.tsx @@ -3,6 +3,7 @@ import { Download, Trash2, X, CheckCircle2, Cpu, Mic, Volume2, AlertTriangle, Re import type { VoiceModelStatus } from '../../../shared/voice'; import { bridge } from '../../lib/bridge'; import { useShallow } from 'zustand/react/shallow'; +import { pickSpeaker } from '../../lib/voicePreference'; import { useVoiceModels } from '../../state/voiceModels'; import { useSettings } from '../../state/settings'; @@ -24,7 +25,10 @@ function ModelRow({ model }: { model: VoiceModelStatus }) { if (model.kind === 'stt') update({ voice: { localModel: model.id, provider: 'local' } }); else if (model.kind === 'kws') update({ voice: { wakeMode: 'kws' } }); else if (model.kind === 'vad') update({ voice: { neuralVad: true } }); - else update({ speech: { localModel: model.id, provider: 'local', localSpeaker: model.speakers?.[0]?.id ?? 0 } }); + else { + const { speech } = useSettings.getState().settings; + update({ speech: { localModel: model.id, provider: 'local', localSpeaker: pickSpeaker(model, speech.language || 'fr-FR', speech.voiceGender ?? 'male') } }); + } }; const neuralVad = useSettings((s) => s.settings.voice.neuralVad); const activeNow = model.kind === 'kws' ? wakeMode === 'kws' : model.kind === 'vad' ? neuralVad : isActive; diff --git a/src/components/settings/SettingsDrawer.tsx b/src/components/settings/SettingsDrawer.tsx index 84a0f98..83dfa54 100644 --- a/src/components/settings/SettingsDrawer.tsx +++ b/src/components/settings/SettingsDrawer.tsx @@ -5,6 +5,8 @@ import { HermesClient, discoverHermesUrl, hermesUrlCandidates } from '../../serv import { listSystemVoices } from '../../services/voice/tts'; import { speech } from '../../services/voice/speech'; import { ensurePreferredVoice } from '../../services/voice/voicePreference'; +import { pickSpeaker, resolveEdgeVoice } from '../../lib/voicePreference'; +import type { EdgeVoice } from '../../../shared/voice'; import { listMicrophones } from '../../services/voice/capture'; import { transcribeWav } from '../../services/voice/stt'; import { encodeWav } from '../../services/voice/wav'; @@ -86,8 +88,18 @@ export function SettingsDrawer({ onClose }: Props) { const [sttTest, setSttTest] = useState({ status: 'idle', message: '' }); const [ttsTest, setTtsTest] = useState({ status: 'idle', message: '' }); const [voices, setVoices] = useState(listSystemVoices()); + const [edgeVoices, setEdgeVoices] = useState([]); const [webhookSecretVisible, setWebhookSecretVisible] = useState(false); + const speechProvider = settings.speech.provider; + useEffect(() => { + if (speechProvider !== 'edge' || edgeVoices.length) return; + bridge() + ?.voice.edgeVoices() + .then(setEdgeVoices) + .catch((err: Error) => setTtsTest({ status: 'fail', message: `Liste des voix Edge indisponible : ${err.message}` })); + }, [speechProvider, edgeVoices.length]); + useEffect(() => { const refresh = () => setVoices(listSystemVoices()); refresh(); @@ -359,6 +371,12 @@ export function SettingsDrawer({ onClose }: Props) { )} update({ voice: { localCommands: v } })} label="Commandes locales instantanées" hint="« Verrouille la session », « monte le son », « ouvre Spotify », « regarde mon écran »… exécutées sur ce PC sans passer par Hermes." /> + update({ voice: { micProcessing: v } })} + label="Traitement du micro par Chromium (écho, bruit, gain automatique)" + hint="Désactivez-le si les transcriptions sont approximatives avec un casque ou un bon micro : ces filtres déforment la voix avant la reconnaissance. Gardez-le activé avec des haut-parleurs (sinon la voix de l’assistant est réentendue par le micro)." + />
@@ -374,7 +392,11 @@ export function SettingsDrawer({ onClose }: Props) { - S’applique à tous les moteurs : voix locale (Piper Tom ou Pierre pour le masculin, téléchargée automatiquement si besoin), voix OpenAI (onyx / nova), voix système Windows (Paul / Hortense). Kokoro n’a pas de voix française masculine. + + S’applique à tous les moteurs : Edge (Henri / Denise), voix locale (Supertonic 3, cinq voix de chaque genre, téléchargé automatiquement si besoin), API OpenAI (onyx / nova), voix système Windows (Paul / Hortense). + {settings.speech.provider === 'google-free' && ' Google Translate n’a qu’une voix féminine : ce choix n’a pas d’effet avec ce moteur.'} + {settings.speech.provider === 'local' && settings.speech.localModel === 'kokoro-v1' && ' Kokoro n’a qu’une voix française, féminine et avec accent : la voix masculine bascule sur Supertonic 3.'} +
@@ -388,29 +410,62 @@ export function SettingsDrawer({ onClose }: Props) { + {settings.speech.provider === 'local' ? `voix active : ${voiceModels.find((m) => m.id === settings.speech.localModel)?.speakers?.find((s) => s.id === settings.speech.localSpeaker)?.name ?? settings.speech.localModel}` - : `moteur : ${settings.speech.provider}`} + : settings.speech.provider === 'edge' + ? `voix active : ${resolveEdgeVoice(settings.speech.edgeVoice ?? '', settings.speech.language, settings.speech.voiceGender ?? 'male')}` + : `moteur : ${settings.speech.provider}`}
- { + update({ speech: { provider: e.target.value as typeof settings.speech.provider } }); + void ensurePreferredVoice().then((m) => m && setTtsTest({ status: 'ok', message: m })); + }} + > + + + - +
+ {settings.speech.provider === 'edge' && ( +
+ + + Mêmes voix que la lecture à voix haute d’Edge : Henri, Denise, Rémy, Vivienne, Éloise (fr-FR), plus les voix canadiennes, suisses et belges. Aucune donnée locale ; chaque phrase est synthétisée en ligne. +
+ )} {settings.speech.provider === 'openai-compatible' && ( <>
@@ -424,7 +479,7 @@ export function SettingsDrawer({ onClose }: Props) {
- update({ speech: { voice: e.target.value } })} /> + update({ speech: { voice: e.target.value } })} />
@@ -444,7 +499,7 @@ export function SettingsDrawer({ onClose }: Props) { {settings.speech.provider === 'local' && ( installedModels(voiceModels, 'tts').length === 0 ? ( ) : (
@@ -452,7 +507,8 @@ export function SettingsDrawer({ onClose }: Props) { diff --git a/src/lib/voicePreference.ts b/src/lib/voicePreference.ts index fe1a668..cae17bb 100644 --- a/src/lib/voicePreference.ts +++ b/src/lib/voicePreference.ts @@ -1,13 +1,18 @@ /** Voice gender preference applied to every TTS provider (pure helpers, unit tested). */ -import type { VoiceModelStatus } from '../../shared/voice'; +import type { VoiceModelStatus, VoiceSpeaker } from '../../shared/voice'; +import { defaultEdgeVoice, edgeVoiceGender } from '../../shared/edgeTts'; export type VoiceGender = 'male' | 'female'; -const MALE_HINTS = /\b(homme|male|masculin|paul|thomas|claude|henri|guillaume|mathieu|antoine|nicolas|denis|pierre|tom|adam|michael|eric|liam|george|lewis|daniel|fenrir|puck|onyx|echo|david|mark|richard|james|ryan|guy)\b/i; -const FEMALE_HINTS = /\b(femme|female|f[ée]minin|hortense|julie|denise|eloise|am[ée]lie|audrey|siwis|jessica|heart|bella|sarah|nicole|sky|alloy|nova|shimmer|zira|aria|jenny|emma|isabella|sophie|charlotte|vivienne|coral|sage)\b/i; +const MALE_HINTS = + /\b(homme|male|masculin|paul|thomas|claude|henri|remy|rémy|gerard|guillaume|mathieu|antoine|nicolas|denis|pierre|tom|adam|michael|eric|liam|george|lewis|daniel|fenrir|puck|onyx|echo|david|mark|richard|james|ryan|guy|dylan|aiden|uncle fu|andrew|brian|fabrice|jean|thierry)\b/i; +const FEMALE_HINTS = + /\b(femme|female|f[ée]minin|hortense|julie|denise|eloise|vivienne|charline|sylvie|ariane|am[ée]lie|audrey|siwis|jessica|heart|bella|sarah|nicole|sky|alloy|nova|shimmer|zira|aria|jenny|emma|ava|isabella|sophie|charlotte|coral|sage|vivian|serena|sohee|ono anna)\b/i; -/** Best-effort gender from a voice or speaker label ("Piper Tom (homme, français)", "Microsoft Paul", "am_adam"). */ +/** Best-effort gender from a voice or speaker label ("Piper Tom (homme, français)", "Microsoft Paul", "am_adam", "fr-FR-HenriNeural"). */ export function inferGender(name: string): VoiceGender | undefined { + const edge = edgeVoiceGender(name); + if (edge) return edge; const n = name.replace(/_/g, ' '); if (/^(am|bm|em|hm|im|jm|pm|zm)\b/i.test(n) || MALE_HINTS.test(n)) return 'male'; if (/^(af|bf|ef|ff|hf|if|jf|pf|zf)\b/i.test(n) || FEMALE_HINTS.test(n)) return 'female'; @@ -19,6 +24,13 @@ export function defaultOpenAiVoice(gender: VoiceGender): string { return gender === 'male' ? 'onyx' : 'nova'; } +/** Edge voice to use: the explicit choice when it matches the gender, otherwise the language default. */ +export function resolveEdgeVoice(explicit: string, language: string, gender: VoiceGender): string { + const chosen = explicit.trim(); + if (chosen && (edgeVoiceGender(chosen) ?? gender) === gender) return chosen; + return defaultEdgeVoice(language, gender); +} + /** Rank system voices: language first, then gender, then quality hints. */ export function rankSystemVoice(v: { name: string; lang: string; localService?: boolean }, lang: string, gender: VoiceGender): number { const name = v.name.toLowerCase(); @@ -38,16 +50,39 @@ export interface LocalVoiceChoice { speaker: number; } -/** Installed local voice matching language + gender, or null. */ +/** Local models from best to worst French rendering; unknown models come last. */ +const LOCAL_QUALITY: Record = { 'supertonic-3': 0, 'kokoro-v1': 1, 'piper-fr-upmc': 2, 'piper-fr-tom': 3, 'piper-fr-siwis': 4 }; + +export function localQualityRank(modelId: string): number { + return LOCAL_QUALITY[modelId] ?? 9; +} + +function speakerGender(sp: VoiceSpeaker): VoiceGender | undefined { + return sp.gender === 'm' ? 'male' : sp.gender === 'f' ? 'female' : inferGender(sp.name); +} + +function speakerSpeaks(sp: VoiceSpeaker, lang: string): boolean { + const spLang = (sp.lang || '').toLowerCase(); + return !spLang || spLang === lang || spLang === 'multi'; +} + +/** First speaker of a model matching language + gender; falls back to any speaker of the language, then the first one. */ +export function pickSpeaker(model: Pick, lang: string, gender: VoiceGender): number { + const l = lang.toLowerCase().split('-')[0]; + const speakers = model.speakers ?? []; + const exact = speakers.find((sp) => speakerSpeaks(sp, l) && speakerGender(sp) === gender); + const sameLang = speakers.find((sp) => speakerSpeaks(sp, l)); + return (exact ?? sameLang ?? speakers[0])?.id ?? 0; +} + +/** Installed local voice matching language + gender (best model first), or null. */ export function findLocalVoice(models: VoiceModelStatus[], lang: string, gender: VoiceGender): LocalVoiceChoice | null { const l = lang.toLowerCase().split('-')[0]; - const installed = models.filter((m) => m.kind === 'tts' && m.installed); + const installed = models.filter((m) => m.kind === 'tts' && m.installed).sort((a, b) => localQualityRank(a.id) - localQualityRank(b.id)); for (const model of installed) { for (const sp of model.speakers ?? []) { - const spLang = (sp.lang || '').toLowerCase(); - if (spLang && spLang !== l && spLang !== 'multi') continue; - const g = (sp as { gender?: string }).gender === 'm' ? 'male' : (sp as { gender?: string }).gender === 'f' ? 'female' : inferGender(sp.name); - if (g === gender) return { modelId: model.id, speaker: sp.id }; + if (!speakerSpeaks(sp, l)) continue; + if (speakerGender(sp) === gender) return { modelId: model.id, speaker: sp.id }; } } return null; @@ -57,10 +92,19 @@ export function findLocalVoice(models: VoiceModelStatus[], lang: string, gender: export function suggestedDownload(models: VoiceModelStatus[], lang: string, gender: VoiceGender): string | null { const l = lang.toLowerCase().split('-')[0]; if (l !== 'fr') return null; - const wanted = gender === 'male' ? ['piper-fr-tom', 'piper-fr-upmc'] : ['kokoro-v1', 'piper-fr-siwis']; + const wanted = gender === 'male' ? ['supertonic-3', 'piper-fr-tom', 'piper-fr-upmc'] : ['supertonic-3', 'kokoro-v1', 'piper-fr-siwis']; for (const id of wanted) { const m = models.find((x) => x.id === id); if (m && !m.installed) return id; } return null; } + +/** Best local model in the catalog for the language that is not installed yet (null when the best is already there). */ +export function bestLocalUpgrade(models: VoiceModelStatus[], lang: string): string | null { + const l = lang.toLowerCase().split('-')[0]; + const best = models + .filter((m) => m.kind === 'tts' && (m.languages.includes(l) || m.languages.includes('multi'))) + .sort((a, b) => localQualityRank(a.id) - localQualityRank(b.id))[0]; + return best && !best.installed ? best.id : null; +} diff --git a/src/services/voice/capture.ts b/src/services/voice/capture.ts index fbd5059..4ad99e6 100644 --- a/src/services/voice/capture.ts +++ b/src/services/voice/capture.ts @@ -49,6 +49,8 @@ export interface CaptureCallbacks { export interface CaptureOptions { deviceId?: string; + /** Chromium's echo cancellation / noise suppression / auto gain (default on). Off keeps the raw signal for the recogniser. */ + micProcessing?: boolean; mode: CaptureMode; vad?: Partial; callbacks: CaptureCallbacks; @@ -124,9 +126,9 @@ export class MicCapture { const constraints: MediaStreamConstraints = { audio: { deviceId: options.deviceId ? { exact: options.deviceId } : undefined, - echoCancellation: true, - noiseSuppression: true, - autoGainControl: true, + echoCancellation: options.micProcessing !== false, + noiseSuppression: options.micProcessing !== false, + autoGainControl: options.micProcessing !== false, channelCount: 1 } }; diff --git a/src/services/voice/tts.ts b/src/services/voice/tts.ts index 91e38b4..ca3a97c 100644 --- a/src/services/voice/tts.ts +++ b/src/services/voice/tts.ts @@ -1,16 +1,17 @@ /** * Text-to-speech engine with a sentence queue, bounded prefetching and Web Audio playback so - * the HUD reacts to the actual waveform. Providers: in-app sherpa-onnx (Kokoro / Piper), - * OpenAI-compatible /v1/audio/speech, system voices, and the legacy Google Translate endpoint. + * the HUD reacts to the actual waveform. Providers: Microsoft Edge neural voices (online, free), + * in-app sherpa-onnx (Supertonic / Kokoro / Piper), OpenAI-compatible /v1/audio/speech, system + * voices, and the legacy Google Translate endpoint (one feminine voice per language). */ import { Log } from '../../lib/log'; -import { defaultOpenAiVoice, rankSystemVoice } from '../../lib/voicePreference'; +import { defaultOpenAiVoice, rankSystemVoice, resolveEdgeVoice } from '../../lib/voicePreference'; import { bridge } from '../../lib/bridge'; import { chunkForSpeech, cleanForSpeech, extractSentences } from '../../lib/text'; import { httpFetch } from '../../lib/transport'; import { audioBus } from './audioBus'; -export type TtsProvider = 'openai-compatible' | 'system' | 'google-free' | 'local' | 'off'; +export type TtsProvider = 'edge' | 'openai-compatible' | 'system' | 'google-free' | 'local' | 'off'; export interface TtsConfig { provider: TtsProvider; @@ -27,6 +28,8 @@ export interface TtsConfig { localModel: string; /** Speaker id inside the local model. */ localSpeaker: number; + /** Microsoft Edge voice short name (provider 'edge'); empty = automatic from language + gender. */ + edgeVoice?: string; /** 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. */ @@ -179,8 +182,9 @@ export class TtsEngine { } private prefetch(text: string, gen: number): Promise { + const provider = this.config.provider; const task = - this.config.provider === 'google-free' ? this.fetchGoogle(text) : this.config.provider === 'local' ? this.fetchLocal(text) : this.fetchOpenAi(text); + provider === 'google-free' ? this.fetchGoogle(text) : provider === 'local' ? this.fetchLocal(text) : provider === 'edge' ? this.fetchEdge(text) : this.fetchOpenAi(text); return task .then(async (bytes) => { if (gen !== this.generation || !bytes) return null; @@ -228,12 +232,23 @@ export class TtsEngine { modelId: this.config.localModel, text, speaker: this.config.localSpeaker, - speed: Math.max(0.5, Math.min(2, this.config.speed || 1)) + speed: Math.max(0.5, Math.min(2, this.config.speed || 1)), + language: this.config.language || 'fr-FR' }); Log.debug('tts', `local synthesis ${result.durationMs} ms for ${result.audioSec.toFixed(1)}s of audio`); return result.wav; } + /** Microsoft Edge neural voices through the main process (no key, online). */ + private async fetchEdge(text: string): Promise { + const api = bridge(); + if (!api) throw new Error('Les voix Edge nécessitent l’application Electron.'); + const voice = resolveEdgeVoice(this.config.edgeVoice ?? '', this.config.language || 'fr-FR', this.config.voiceGender ?? 'male'); + const result = await api.voice.edgeSynthesize({ text, voice, speed: Math.max(0.5, Math.min(2, this.config.speed || 1)) }); + Log.debug('tts', `edge synthesis (${voice}) ${result.durationMs} ms, ${result.mp3.byteLength} bytes`); + return result.mp3; + } + private async fetchGoogle(text: string): Promise { const url = `https://translate.google.com/translate_tts?ie=UTF-8&tl=${encodeURIComponent(this.config.language.split('-')[0] || 'fr')}&client=tw-ob&q=${encodeURIComponent(text.slice(0, 200))}`; const res = await httpFetch({ diff --git a/src/services/voice/voiceController.ts b/src/services/voice/voiceController.ts index 73025f7..0419028 100644 --- a/src/services/voice/voiceController.ts +++ b/src/services/voice/voiceController.ts @@ -128,6 +128,7 @@ class VoiceController { } await this.wake.start({ deviceId: settings.micDeviceId || undefined, + micProcessing: settings.micProcessing ?? true, neuralVad, vad: { silenceMs: settings.silenceMs, speechRatio: SENSITIVITY_RATIO[sensitivity], minRms: SENSITIVITY_MIN_RMS[sensitivity] }, callbacks: { @@ -249,6 +250,7 @@ class VoiceController { await audioBus.resume(); await this.capture.start({ deviceId: settings.micDeviceId || undefined, + micProcessing: settings.micProcessing ?? true, mode: settings.captureMode, vad: { silenceMs: settings.silenceMs, diff --git a/src/services/voice/voicePreference.ts b/src/services/voice/voicePreference.ts index 7e61f2e..b4b2d1c 100644 --- a/src/services/voice/voicePreference.ts +++ b/src/services/voice/voicePreference.ts @@ -1,44 +1,64 @@ /** * Applies the preferred voice gender to the active TTS provider: switches the local model/speaker, - * downloads a matching French voice when none is installed, and logs what it did. + * downloads a matching French voice when none is installed, resets an Edge voice of the other + * gender, and explains providers that cannot honour the choice (Google Translate). */ import { Log } from '../../lib/log'; -import { findLocalVoice, inferGender, suggestedDownload } from '../../lib/voicePreference'; +import { bestLocalUpgrade, findLocalVoice, resolveEdgeVoice, suggestedDownload } from '../../lib/voicePreference'; import { useSettings } from '../../state/settings'; import { useVoiceModels } from '../../state/voiceModels'; let downloading: string | null = null; -/** Make the local voice match `speech.voiceGender`. Returns a short status message. */ -export async function ensurePreferredVoice(): Promise { +const genderLabel = (g: 'male' | 'female') => (g === 'male' ? 'masculine' : 'féminine'); + +/** + * Make the active provider match `speech.voiceGender`. Returns a short status message. + * With `upgrade`, the best local model for the language is downloaded even if a lesser voice exists. + */ +export async function ensurePreferredVoice(options: { upgrade?: boolean } = {}): Promise { const { settings, update } = useSettings.getState(); const { speech } = settings; const gender = speech.voiceGender ?? 'male'; + const lang = speech.language || 'fr-FR'; + + if (speech.provider === 'edge') { + const voice = resolveEdgeVoice(speech.edgeVoice ?? '', lang, gender); + if (voice !== (speech.edgeVoice ?? '').trim() && speech.edgeVoice) update({ speech: { edgeVoice: '' } }); + return `Voix ${genderLabel(gender)} : ${voice.split('-')[2]?.replace(/(Multilingual)?Neural$/, '') ?? voice} (Edge)`; + } + if (speech.provider === 'google-free') { + return gender === 'male' + ? 'Google Translate n’a qu’une voix féminine par langue : choisissez « Microsoft Edge » ou une voix locale pour une voix masculine.' + : ''; + } if (speech.provider !== 'local') return ''; + const models = useVoiceModels.getState().models; if (!models.length) return ''; - const lang = speech.language || 'fr-FR'; const current = models.find((m) => m.id === speech.localModel); const currentSpeaker = current?.speakers?.find((s) => s.id === speech.localSpeaker); - const currentGender = currentSpeaker ? (currentSpeaker as { gender?: string }).gender === 'm' ? 'male' : (currentSpeaker as { gender?: string }).gender === 'f' ? 'female' : inferGender(currentSpeaker.name) : undefined; - if (current?.installed && currentGender === gender) return ''; + const currentGender = currentSpeaker ? (currentSpeaker.gender === 'm' ? 'male' : currentSpeaker.gender === 'f' ? 'female' : undefined) : undefined; + const upgrade = options.upgrade ? bestLocalUpgrade(models, lang) : null; + if (current?.installed && currentGender === gender && !upgrade) return ''; - const choice = findLocalVoice(models, lang, gender); + const choice = upgrade ? null : findLocalVoice(models, lang, gender); if (choice) { update({ speech: { localModel: choice.modelId, localSpeaker: choice.speaker } }); const name = models.find((m) => m.id === choice.modelId)?.speakers?.find((s) => s.id === choice.speaker)?.name ?? choice.modelId; Log.info('tts', `voice preference ${gender}: ${name}`); - return `Voix ${gender === 'male' ? 'masculine' : 'féminine'} : ${name}`; + return `Voix ${genderLabel(gender)} : ${name}`; } - const download = suggestedDownload(models, lang, gender); + const download = upgrade ?? suggestedDownload(models, lang, gender); if (!download || downloading === download) return download ? 'Téléchargement de la voix en cours…' : ''; downloading = download; - Log.info('tts', `no ${gender} voice installed, downloading ${download}`); + Log.info('tts', `${upgrade ? 'upgrading local voice' : `no ${gender} voice installed`}, downloading ${download}`); try { await useVoiceModels.getState().download(download); const after = findLocalVoice(useVoiceModels.getState().models, lang, gender); if (after) update({ speech: { localModel: after.modelId, localSpeaker: after.speaker } }); - return after ? `Voix ${gender === 'male' ? 'masculine' : 'féminine'} installée.` : 'Voix téléchargée.'; + const name = after ? useVoiceModels.getState().models.find((m) => m.id === after.modelId)?.name : undefined; + return after ? `Voix ${genderLabel(gender)} installée : ${name ?? after.modelId}.` : 'Voix téléchargée.'; } catch (err) { Log.warn('tts', `voice download failed: ${(err as Error).message}`); return `Téléchargement impossible : ${(err as Error).message}`; diff --git a/src/services/voice/wakeListener.ts b/src/services/voice/wakeListener.ts index 780ccd9..ee8a431 100644 --- a/src/services/voice/wakeListener.ts +++ b/src/services/voice/wakeListener.ts @@ -74,7 +74,7 @@ export class WakeListener { return this.phase; } - async start(options: { deviceId?: string; vad?: Partial; neuralVad?: boolean; callbacks: WakeCallbacks }): Promise { + async start(options: { deviceId?: string; micProcessing?: boolean; vad?: Partial; neuralVad?: boolean; callbacks: WakeCallbacks }): Promise { if (this.phase !== 'off') return; this.callbacks = options.callbacks; this.vadOptions = options.vad ?? {}; @@ -86,9 +86,9 @@ export class WakeListener { this.stream = await navigator.mediaDevices.getUserMedia({ audio: { deviceId: options.deviceId ? { exact: options.deviceId } : undefined, - echoCancellation: true, - noiseSuppression: true, - autoGainControl: true, + echoCancellation: options.micProcessing !== false, + noiseSuppression: options.micProcessing !== false, + autoGainControl: options.micProcessing !== false, channelCount: 1 } }); diff --git a/src/state/settings.ts b/src/state/settings.ts index 3b5e193..da87411 100644 --- a/src/state/settings.ts +++ b/src/state/settings.ts @@ -26,6 +26,8 @@ export interface VoiceSettings extends SttConfig { neuralVad: boolean; /** Execute short system intents locally (lock, volume, open app…) instead of asking Hermes. */ localCommands: boolean; + /** Chromium mic processing (echo cancellation, noise suppression, auto gain). Off often transcribes better on a headset. */ + micProcessing: boolean; } export interface SpeechSettings extends TtsConfig { @@ -110,10 +112,12 @@ export const DEFAULT_SETTINGS: Settings = { kwsSensitivity: 3, neuralVad: true, localCommands: true, + micProcessing: true, localModel: 'whisper-base' }, speech: { - provider: 'openai-compatible', + // Edge neural voices speak out of the box (no server, no key) with a real masculine/feminine choice. + provider: 'edge', apiUrl: 'http://127.0.0.1:8000/v1', apiKey: '', model: 'tts-1', @@ -123,8 +127,9 @@ export const DEFAULT_SETTINGS: Settings = { systemVoice: '', language: 'fr-FR', volume: 1, - localModel: 'kokoro-v1', - localSpeaker: 30, + localModel: 'supertonic-3', + localSpeaker: 6, + edgeVoice: '', voiceGender: 'male', timbre: 'jarvis', autoSpeak: true, diff --git a/tests/edgeTts.test.ts b/tests/edgeTts.test.ts new file mode 100644 index 0000000..c826115 --- /dev/null +++ b/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(""); + expect(ssml).toContain("rate='+25%'"); + expect(ssml).toContain('Tom & Jerry <3 "ok"'); + expect(escapeXml("l'été")).toBe('l'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', '', 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')).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(); + }); +}); diff --git a/tests/voicePreference.test.ts b/tests/voicePreference.test.ts index 1c50a21..6bf1abc 100644 --- a/tests/voicePreference.test.ts +++ b/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 };