diff --git a/docs/homelab-integration.md b/docs/homelab-integration.md
index 6537d96..7472084 100644
--- a/docs/homelab-integration.md
+++ b/docs/homelab-integration.md
@@ -14,7 +14,8 @@ it** — endpoints and aliases drift, and this file is a snapshot (2026-06-06),
     not LiteLLM. Use `30401` for off-cluster LiteLLM. `confirm` resolved.
 - **Speech-to-text (ADR-033):** the same gateway serves `POST /v1/audio/transcriptions` for
   `iguana/kb-whisper` (primary, local) and `berget/kb-whisper` (fallback, EU cloud — private audio
-  leaves the homelab if it is used). **Call it via the NodePort / in-cluster address above, NOT
+  leaves the homelab if it is used: when the primary fails **or returns an empty transcript**,
+  e.g. a silent or music-only file; the transcript page then says so, #52). **Call it via the NodePort / in-cluster address above, NOT
   `https://llm-api.d-ma.be`:** that public ingress (openresty) returns `413` for bodies over
   roughly 8–10 MB (~5 minutes of 16 kHz WAV), while the NodePort took 174 MB (90 minutes) in one
   request (measured 2026-10-01, `docs/research/audio-length-ceiling-2026-10-01.md`). Send multipart
diff --git a/docs/use-cases/audio_upload.feature b/docs/use-cases/audio_upload.feature
index e45c465..cd3ed30 100644
--- a/docs/use-cases/audio_upload.feature
+++ b/docs/use-cases/audio_upload.feature
@@ -240,6 +240,11 @@ Feature: Upload an audio recording, get a private Swedish transcript, discuss it
     Then it is transcribed anyway and its audio step says how long the audio really is
     And a complete recording whose header over-estimated its length is not refused
 
+  Scenario: A transcript made by the cloud fallback says the audio left the homelab
+    When the transcript was produced by an endpoint that is not local
+    Then its page says in plain words that the audio left the homelab and names the provider
+    And a locally transcribed recording carries no such note
+
   Scenario: A full queue is a retry, not an error
     When too many recordings are already waiting
     Then the upload is answered as busy, its row is failed honestly and its audio is deleted
diff --git a/test/acceptance/scenario_coverage_test.go b/test/acceptance/scenario_coverage_test.go
index 9bbf026..0dfcbba 100644
--- a/test/acceptance/scenario_coverage_test.go
+++ b/test/acceptance/scenario_coverage_test.go
@@ -122,6 +122,8 @@ var scenarioCoverage = map[string]string{
 	"I can ask about my recording and get a grounded answer":                    "TestUploadChatPost_SendsTheOwnersTranscriptWithTheUploadBudget",
 	"A long recording is not cut to its first third":                            "TestAnswerMaxCharsOverridesTheServiceCap",
 
+	"A transcript made by the cloud fallback says the audio left the homelab": "TestUploadStatus_ACloudServedTranscriptSaysTheAudioLeftTheHomelab",
+
 	// audio_upload.feature, ADR-034
 	"Two engines transcribe the audio and their disagreements are reconciled": "TestEnsemble_BothEnginesRunInOrderAndTheirDisagreementIsReconciled",
 	"Trivial disagreements never reach the model":                             "TestReconcile_TrivialDisputesAreResolvedWithoutAskingTheModel",