cmd/tapir/main.go

@@ -207,6 +207,27 @@ func cmdServe(ctx context.Context, log *slog.Logger) error {
 		log.Info("web chat enabled (stored-transcript only)", "models", chatModels(cfg))
 	}
 
+	// Audio upload -> private transcript (ADR-033). Off unless TAPIR_UPLOADS_ENABLED:
+	// the image must carry ffmpeg first. The worker is IN-PROCESS and one job at a
+	// time, so it inherits the single-replica assumption below (its queue is
+	// process-local); it stops with the same ctx as the server.
+	intake, worker, err := buildUploads(ctx, cfg, st, log)
+	if err != nil {
+		return err
+	}
+	if intake != nil {
+		app.Uploads = intake
+		app.UploadLimits = uploadLimits(cfg)
+		go worker.Run(ctx)
+		log.Info("audio upload enabled", "model", cfg.TranscribeModel, "fallback", cfg.TranscribeFallbackModel,
+			"max_mb", cfg.UploadMaxBytes>>20, "max_minutes", int(cfg.UploadMaxDuration.Minutes()))
+		log.Warn("audio upload assumes a SINGLE replica: the transcription queue is process-local (ADR-033, ADR-018)")
+		if cfg.TranscribeFallbackModel != "" {
+			log.Warn("audio upload fallback is a CLOUD endpoint: if the primary fails, private audio leaves the homelab",
+				"fallback", cfg.TranscribeFallbackModel)
+		}
+	}
+
 	// User onboarding is handled by the IdP (Authentik invite flow), not Tapir —
 	// the Dex local-password provisioning path was removed (ADR-019). An
 	// authenticated subject with no Tapir user is routed to /register.