extract shared whisper transcribe helper, use in file-browser and pi stt routes

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

src/servers/api/stt/transcribe.ts

@@ -0,0 +1,89 @@
+// Whisper transcription with language-aware translation.
+//
+// Strategy: detect the audio's language, then transcribe in that language.
+// Only ask Whisper to translate (which is English-only) when the detected
+// language is NOT one the user speaks — i.e. they wouldn't understand the
+// raw transcript anyway.
+
+type TranscribeArgs = {
+  file: File | Blob;
+  whisperUrl: string;
+  spokenLanguages: string[];
+};
+
+export type TranscribeResult = {
+  text: string;
+  detectedLanguage: string;
+  translated: boolean;
+};
+
+// whisper.cpp's "language" field uses full names ("english"); ISO codes live in
+// `language_probabilities`. Map covers what the user can pick in Profile settings.
+const LANG_NAME_TO_ISO: Record<string, string> = {
+  english: 'en',
+  portuguese: 'pt',
+  spanish: 'es',
+  french: 'fr',
+  german: 'de',
+  italian: 'it',
+  dutch: 'nl',
+  russian: 'ru',
+  chinese: 'zh',
+  japanese: 'ja',
+  korean: 'ko',
+};
+
+export async function transcribeAudio({ file, whisperUrl, spokenLanguages }: TranscribeArgs): Promise<TranscribeResult> {
+  const base = whisperUrl.replace(/\/+$/, '');
+
+  // Step 1: detect language. Bias toward the user's spoken languages — Whisper's
+  // raw auto-detect is unreliable on short clips and often picks English by default.
+  const detectForm = new FormData();
+  detectForm.append('file', file);
+  detectForm.append('temperature', '0.0');
+  detectForm.append('response_format', 'verbose_json');
+  detectForm.append('detect_language', 'true');
+
+  const detectRes = await fetch(`${base}/inference`, { method: 'POST', body: detectForm });
+  if (!detectRes.ok) throw new Error(`Language detection failed (${detectRes.status})`);
+  const detectJson = (await detectRes.json()) as {
+    language?: string;
+    language_probabilities?: Record<string, number>;
+  };
+
+  const probs = detectJson.language_probabilities;
+  let detectedLanguage: string;
+  if (probs && spokenLanguages.length > 0) {
+    // Pick the spoken language with the highest probability
+    const ranked = spokenLanguages
+      .map((code) => [code, probs[code] ?? 0] as const)
+      .sort((a, b) => b[1] - a[1]);
+    detectedLanguage = ranked[0]?.[0] ?? spokenLanguages[0]!;
+  } else if (probs) {
+    // No spoken-language hint: take the highest-probability ISO code
+    const top = Object.entries(probs).sort((a, b) => b[1] - a[1])[0];
+    detectedLanguage = top?.[0] ?? 'en';
+  } else {
+    // No probabilities field (non-whisper.cpp backend) — try to map the name
+    const raw = (detectJson.language ?? 'en').toLowerCase();
+    detectedLanguage = LANG_NAME_TO_ISO[raw] ?? raw;
+  }
+
+  // Step 2: translate only when the user doesn't speak the detected language
+  const translated = spokenLanguages.length > 0 && !spokenLanguages.includes(detectedLanguage);
+
+  // Step 3: full transcription
+  const transcribeForm = new FormData();
+  transcribeForm.append('file', file);
+  transcribeForm.append('temperature', '0.0');
+  transcribeForm.append('temperature_inc', '0.2');
+  transcribeForm.append('response_format', 'text');
+  transcribeForm.append('language', detectedLanguage);
+  if (translated) transcribeForm.append('translate', 'true');
+
+  const res = await fetch(`${base}/inference`, { method: 'POST', body: transcribeForm });
+  if (!res.ok) throw new Error(`Transcription failed (${res.status})`);
+  const text = (await res.text()).trim();
+
+  return { text, detectedLanguage, translated };
+}