Merge branch 'feat/dictation-silence-vad' into develop

Self-host Silero VAD / onnxruntime-web assets under /vad/ so streaming
dictation loads its wasm backend (fixes the 'text/html' MIME runtime error).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

apps/client/package.json

@@ -3,8 +3,8 @@
   "private": true,
   "version": "0.93.0",
   "scripts": {
-    "dev": "vite",
-    "build": "tsc && vite build",
+    "dev": "node scripts/copy-vad-assets.mjs && vite",
+    "build": "node scripts/copy-vad-assets.mjs && tsc && vite build",
     "lint": "eslint .",
     "preview": "vite preview",
     "format": "prettier --write \"src/**/*.tsx\" \"src/**/*.ts\"",

apps/client/scripts/copy-vad-assets.mjs

@@ -0,0 +1,59 @@
+// Self-host the @ricky0123/vad-web + onnxruntime-web runtime assets under
+// apps/client/public/vad/.
+//
+// WHY THIS EXISTS:
+// Both vad-web and onnxruntime-web resolve their assets by URL *at runtime* (the
+// VAD audio worklet + Silero model, and ORT's wasm/mjs backend). In vad-web
+// 0.0.30 the default baseAssetPath / onnxWASMBasePath is "./" — i.e. relative to
+// the current page URL — NOT a CDN. In this SPA that "./" request hits the
+// client-side catch-all route and gets served index.html (text/html), so the
+// onnxruntime ESM/wasm backend fails to initialize ("'text/html' is not a valid
+// JavaScript MIME type"). We fix that by copying the four needed files into
+// public/vad/ and pointing both path constants at the fixed absolute "/vad/".
+//
+// These copies are NOT committed (the ORT wasm is ~26 MB); this script runs
+// before `dev` and `build` (see package.json) to repopulate them from
+// node_modules. It is idempotent: it (re)creates the dir and overwrites.
+
+import { createRequire } from "node:module";
+import { fileURLToPath } from "node:url";
+import path from "node:path";
+import fs from "node:fs";
+
+const require = createRequire(import.meta.url);
+const here = path.dirname(fileURLToPath(import.meta.url));
+const outDir = path.join(here, "..", "public", "vad");
+
+// vad-web exposes ./package.json, so derive its dist dir from there.
+const vadDist = path.join(
+  path.dirname(require.resolve("@ricky0123/vad-web/package.json")),
+  "dist",
+);
+
+// onnxruntime-web's "exports" map does NOT expose ./package.json, so resolving
+// it would throw ERR_PACKAGE_PATH_NOT_EXPORTED. It DOES export the exact asset
+// subpaths we need, so resolve those files directly.
+const ortMjs = require.resolve(
+  "onnxruntime-web/ort-wasm-simd-threaded.jsep.mjs",
+);
+const ortWasm = require.resolve(
+  "onnxruntime-web/ort-wasm-simd-threaded.jsep.wasm",
+);
+
+// [absolute source path, output filename]
+const files = [
+  [path.join(vadDist, "vad.worklet.bundle.min.js"), "vad.worklet.bundle.min.js"],
+  [path.join(vadDist, "silero_vad_v5.onnx"), "silero_vad_v5.onnx"],
+  [ortMjs, "ort-wasm-simd-threaded.jsep.mjs"],
+  [ortWasm, "ort-wasm-simd-threaded.jsep.wasm"],
+];
+
+fs.mkdirSync(outDir, { recursive: true });
+for (const [src, name] of files) {
+  if (!fs.existsSync(src)) {
+    console.error(`[copy-vad-assets] missing source: ${src}`);
+    process.exit(1);
+  }
+  fs.copyFileSync(src, path.join(outDir, name));
+  console.log(`[copy-vad-assets] ${name}`);
+}

apps/client/src/features/dictation/hooks/use-streaming-dictation.ts

@@ -32,14 +32,17 @@ interface UseStreamingDictationResult {
 // Sample rate of the audio MicVAD hands to onSpeechEnd (Silero VAD runs at 16k).
 const VAD_SAMPLE_RATE = 16000;
 
-// Asset paths for the VAD worklet and the onnxruntime WASM binaries. For this
-// prototype they are left undefined so the library loads its bundled assets from
-// its default CDN — this avoids fragile rolldown asset-copy config. For a
-// self-hosted / offline / privacy build, copy the vad-web `dist` worklet + the
-// `*.onnx` model and the onnxruntime-web `*.wasm` files into
-// `apps/client/public/vad/` and set these to that local path (e.g. "/vad/").
-const VAD_BASE_ASSET_PATH: string | undefined = undefined;
-const VAD_ONNX_WASM_BASE_PATH: string | undefined = undefined;
+// Asset paths for the VAD worklet/Silero model and the onnxruntime-web WASM
+// binaries. vad-web 0.0.30's default asset path is "./" (relative to the current
+// page URL), NOT a CDN — in this SPA that request hits the client-side catch-all
+// route and returns index.html (text/html), so the onnxruntime ESM/wasm backend
+// fails to initialize. We instead self-host the four needed files (the vad-web
+// worklet + `silero_vad_v5.onnx` model and the onnxruntime-web `*.jsep.mjs`/
+// `*.jsep.wasm`) under `apps/client/public/vad/` — populated by
+// `scripts/copy-vad-assets.mjs`, which runs before `dev`/`build` — and point both
+// paths at the fixed absolute "/vad/".
+const VAD_BASE_ASSET_PATH: string | undefined = "/vad/";
+const VAD_ONNX_WASM_BASE_PATH: string | undefined = "/vad/";
 
 /**
  * Streaming variant of useDictation. Detects speech with a real (Silero) VAD and,