Complete rebuild of voice input on a server-authoritative streaming architecture, replacing the legacy Web Speech / whole-blob / WASM engines and the dead voice-agent layer (~4k lines removed). Speech-to-text (dictation): - Client streams 16 kHz mono PCM16 chunks over /api/dictation/ws with seq/ack ordering; buffered audio is retained and replayed on reconnect - Server transcribes and streams live partial transcripts back; segments auto-commit every ~15s with silence suppression and adaptive finalization timeouts - Local provider (default, zero config): sherpa-onnx models in a forked worker process — auto-download with progress, staged extraction with verification, corrupt-model auto-recovery, idle shutdown after 5 min - Model catalog with settings picker (accuracy/speed ratings, sizes, download/delete): Parakeet TDT v2 (English) and v3 (25 European languages, auto-detected), Whisper base and tiny (multilingual, light) - OpenAI-compatible provider for any Whisper endpoint - Composer overlay with live transcript, volume meter, timer, and cancel / insert / insert-and-send actions; failed transcriptions keep their audio for retry or accepting the partial text as-is - Configurable keyboard shortcut (default mod+alt+v) toggles dictation; Enter confirms and Escape cancels while recording - Overlay is pixel-aligned with the composer (measured footer height, matching paddings/typography/gaps) — no layout shift when toggling Text-to-speech: - Local Kokoro provider (English, 11 voices) synthesized in the same worker via /api/dictation/tts/speak, managed by the shared model pipeline; sentence-pipelined playback keeps time-to-first-audio at ~1 sentence regardless of message length, and stop cancels in-flight synthesis - Sanitizer keeps inline-code content (strips backticks only), reads interword slashes aloud, and removes only absolute file paths Settings: - Voice page unified: a single read-aloud toggle owns all playback options (the confusing "Enable Voice Mode" is gone); a new "Enable voice input" toggle (default on, persisted to settings.json) hides the composer mic entirely when disabled Mobile and transport: - iOS/Android microphone permissions added (dictation was previously impossible on mobile) - Fixed Android WebSocket upgrades: the Capacitor WebView origin (https://localhost) was missing from the packaged-client allowlist, 403-ing every WS connection — root cause of the old mobile SSE lock, which is now removed for all transports Security and conventions: - All HTTP routes sit behind the global /api auth gate; the WS upgrade explicitly validates the UI session and origin, with oc_url_token narrowly allowlisted and covered by tests; the dictation socket mints a fresh URL token before connecting - Routes register before the generic OpenCode proxy; the client goes through runtimeFetch/getRuntimeUrlResolver, and runtime switches reset the dictation socket - VS Code deliberately reports dictation as unavailable (no server process in that runtime) CI: workflow Node bumped 20 -> 22 to match the repo engines and fix better-sqlite3 installs broken by node-gyp@latest on Node 20. New dependency: sherpa-onnx-node (prebuilt N-API; macOS/Linux x64+arm64, Windows x64 — Windows-on-ARM falls back to the OpenAI-compatible provider)
111 lines
3.3 KiB
JavaScript
111 lines
3.3 KiB
JavaScript
/**
|
|
* Sherpa-onnx offline TTS (Kokoro). Runs inside the dictation worker process
|
|
* only — never load the native addon in the main server process.
|
|
*/
|
|
|
|
import { existsSync } from 'fs';
|
|
import path from 'path';
|
|
|
|
import { loadSherpaOnnxNode } from './sherpa-loader.js';
|
|
|
|
function assertFileExists(filePath, label) {
|
|
if (!existsSync(filePath)) {
|
|
throw new Error(`Missing ${label}: ${filePath}`);
|
|
}
|
|
}
|
|
|
|
function float32ToPcm16le(samples) {
|
|
const out = new Int16Array(samples.length);
|
|
for (let i = 0; i < samples.length; i += 1) {
|
|
const clamped = Math.max(-1, Math.min(1, samples[i]));
|
|
out[i] = Math.round(clamped * 32767);
|
|
}
|
|
return Buffer.from(out.buffer, out.byteOffset, out.byteLength);
|
|
}
|
|
|
|
export class SherpaTtsEngine {
|
|
/**
|
|
* @param {{ modelDir: string, files: { model: string, voices: string, tokens: string, espeakData: string }, numThreads?: number }} config
|
|
*/
|
|
constructor(config) {
|
|
const modelPath = path.join(config.modelDir, config.files.model);
|
|
const voicesPath = path.join(config.modelDir, config.files.voices);
|
|
const tokensPath = path.join(config.modelDir, config.files.tokens);
|
|
const dataDir = path.join(config.modelDir, config.files.espeakData);
|
|
|
|
assertFileExists(modelPath, 'TTS model');
|
|
assertFileExists(voicesPath, 'TTS voices');
|
|
assertFileExists(tokensPath, 'TTS tokens');
|
|
assertFileExists(dataDir, 'TTS espeak-ng dataDir');
|
|
|
|
const sherpa = loadSherpaOnnxNode();
|
|
if (typeof sherpa.OfflineTts !== 'function') {
|
|
throw new Error('sherpa-onnx-node OfflineTts is unavailable');
|
|
}
|
|
|
|
this.tts = new sherpa.OfflineTts({
|
|
model: {
|
|
kokoro: {
|
|
model: modelPath,
|
|
voices: voicesPath,
|
|
tokens: tokensPath,
|
|
dataDir,
|
|
lengthScale: 1.0,
|
|
},
|
|
},
|
|
numThreads: config.numThreads ?? 2,
|
|
provider: 'cpu',
|
|
maxNumSentences: 1,
|
|
});
|
|
}
|
|
|
|
/**
|
|
* Synthesize text to PCM16LE.
|
|
* @param {string} text
|
|
* @param {{ speakerId?: number, speed?: number }} [options]
|
|
* @returns {{ pcm16: Buffer, sampleRate: number }}
|
|
*/
|
|
synthesize(text, options = {}) {
|
|
const trimmed = String(text || '').trim();
|
|
if (!trimmed) {
|
|
throw new Error('Cannot synthesize empty text');
|
|
}
|
|
|
|
const audio = this.tts.generate({
|
|
text: trimmed,
|
|
sid: Number.isInteger(options.speakerId) ? options.speakerId : 0,
|
|
speed: typeof options.speed === 'number' && options.speed > 0 ? options.speed : 1.0,
|
|
// Request a copied buffer from sherpa itself: native external-backed
|
|
// typed arrays are rejected by Electron.
|
|
enableExternalBuffer: false,
|
|
});
|
|
|
|
let samples = null;
|
|
if (audio && audio.samples instanceof Float32Array) {
|
|
samples = Float32Array.from(audio.samples);
|
|
} else if (audio && Array.isArray(audio.samples)) {
|
|
samples = Float32Array.from(audio.samples);
|
|
}
|
|
if (!samples) {
|
|
throw new Error('Unexpected sherpa TTS output: missing Float32 samples');
|
|
}
|
|
|
|
const sampleRate =
|
|
audio && typeof audio.sampleRate === 'number' && audio.sampleRate > 0
|
|
? audio.sampleRate
|
|
: typeof this.tts.sampleRate === 'number' && this.tts.sampleRate > 0
|
|
? this.tts.sampleRate
|
|
: 24000;
|
|
|
|
return { pcm16: float32ToPcm16le(samples), sampleRate };
|
|
}
|
|
|
|
free() {
|
|
try {
|
|
this.tts?.free?.();
|
|
} catch {
|
|
// ignore
|
|
}
|
|
}
|
|
}
|