diff --git a/docs/ARCHITECTURE.md b/docs/ARCHITECTURE.md
index e770ef4..69f9085 100644
--- a/docs/ARCHITECTURE.md
+++ b/docs/ARCHITECTURE.md
@@ -279,7 +279,7 @@ rewriting the document.
 | 9 | Nav guidance published on the bus; route requests over HTTP via `telemetry-gw` | **Proposed** | 2026-09-03 |
 | 10 | Map artifacts delivered by `rsync` over LAN only; Valhalla tiles kept as a directory, not a tar | Accepted | 2026-09-03 |
 | 11 | Boot ordering is capture-first: acquisition reaches ready before serving or voice | Accepted | 2026-09-03 |
-| 12 | The Orin owns the car's aux input; the display unit carries no permanent cable | Accepted | 2026-09-03 |
+| 12 | The **tablet** owns the car's aux input; TTS crosses as discrete utterances, not a stream | Accepted | 2026-09-04 |
 | 13 | Reasoning stays in the cloud — a local LLM does not fit beside the voice stack | Accepted | 2026-09-03 |
 | 14 | Recordings are bounded with rotation | Accepted | 2026-09-04 |
 | 15 | Boundary is two simplex channels — lossy stream down, acknowledged request/response up | Accepted | 2026-09-03 |
diff --git a/docs/ORIN-RUNTIME.md b/docs/ORIN-RUNTIME.md
index 05a8dbf..5f5cfcf 100644
--- a/docs/ORIN-RUNTIME.md
+++ b/docs/ORIN-RUNTIME.md
@@ -122,26 +122,54 @@ have run. Two properties matter more than the specific size:
 
 ## Audio
 
-The Orin owns the car's single aux input, via a USB DAC.
+The **tablet** owns the car's single aux input. It is the music player, and that
+role is not moving to the Orin.
 
 ```
-  GPT-SoVITS (TTS) ──┐
-                     ├──▶ PipeWire mixer ──▶ USB DAC ──▶ aux in
-  A2DP sink ─────────┘         │
-  (media from the tablet)      └── ducking: media drops under TTS
+  tablet: media (Spotify etc.) ──┐
+                                 ├──▶ Android mixer ──▶ aux in
+  Orin:   GPT-SoVITS (TTS) ──────┘
+          └── utterances sent over the reliable boundary channel
 
-  mic ──▶ Whisper (ASR)
+  Orin:   mic ──▶ Whisper (ASR)        stays local, never crosses
 ```
 
-Three reasons the aux cable belongs here rather than on the tablet:
+The tablet is the media source, so it holds the aux cable whatever is decided
+about speech. Giving the Orin its own aux line would not free the display unit —
+it would add a second permanent cable to the car and leave the first one in place.
 
-- **The aux cable should belong to the fixed unit.** The display is meant to be
-  removable; anything holding a permanent cable to the car is not removable.
-- **Ducking becomes a local policy** on one box instead of coordination between
-  two. Without it the assistant talks over the music.
-- **The direction works.** Linux is a capable A2DP *sink*, so the tablet can send
-  media here. The reverse — this box as an A2DP source into an Android sink — is
-  not viable, since stock Android builds generally do not enable A2DP sink.
+### TTS crosses as utterances, not as a stream
 
-Unplug the tablet and the car keeps audio and voice. The Orin depends on the
-display unit for nothing.
+An utterance is short, finite, and fully synthesised before it is needed. So it
+ships as a **discrete object over the reliable channel**, not as a real-time audio
+stream: no jitter buffer, no underrun handling, no clock synchronisation, and a
+dropped packet is a retry rather than an audible gap.
+
+The cost is that speech begins only once synthesis *and* transfer complete. For a
+car assistant that is fine — nothing here is lip-synced. If streaming TTS is ever
+wanted, so that speech starts before synthesis finishes, this is the decision to
+revisit.
+
+### Ducking is the tablet's job
+
+Android's `AUDIOFOCUS_GAIN_TRANSIENT_MAY_DUCK` ducks other applications' audio —
+Spotify included — for the duration of a request, then restores it. This is the
+mechanism every navigation app already uses, and it is less work than the PipeWire
+policy it replaces. Cross-application ducking is a solved problem on the tablet
+and would have been a bespoke one on the Orin.
+
+### The microphone stays on the Orin
+
+Whisper runs on the Orin, so its input does too. Audio *in* on one box and audio
+*out* on the other is asymmetric on purpose: each side does the simple thing, and
+a microphone has no reason to reach the head unit.
+
+### Degrade when there is no sink
+
+With no tablet connected the Orin can still hear — the mic is local — but cannot
+speak. The voice stack expires or drops pending utterances rather than queueing
+them unboundedly or blocking on a sink that may never arrive.
+
+The consequence to accept: **unplug the tablet and the car has no voice.** That is
+tolerable because unplugging it also removes the music, so the tablet was already
+load-bearing for audio. Speech does not make it more so.