pub(super) async fn handle_voice_transcribe(
__arg0: State<AppState>,
__arg1: Query<TranscribeQuery>,
body: Bytes,
) -> impl IntoResponseExpand description
POST /api/v1/voice/transcribe?mime=audio/webm&lang=en — body is raw audio.
→ 200 { "text": "..." } · 400 empty body · 501 no backend configured ·
502 upstream/subprocess error.