catalog: promote chatterbox-fast to ready; vibevoice->down; resolve voxtral 8197 collision

- chatterbox-fast experimental -> ready: browser audition verified end-to-end
  (operator confirmed progressive playback "excellent" 2026-06-02).
- vibevoice ready -> down: no container running on irv-ml1 (connection refused);
  catalog status was stale.
- voxtral: NOT a stale typo — its stack genuinely claimed :8197, the port now held
  by the live chatterbox-fast. voxtral is down, so moved IT to :8201 (catalog
  endpoint + source_url, stacks/voxtral/.env.example + README, host .env) rather
  than disturb the live service. No live clash existed (voxtral down) but it was a
  latent deploy-time collision I introduced by placing chatterbox-fast on 8197.

No catalog_version bump (status changes + endpoint correction, additive). Validates
against the schema.

docs/asset-engine/services.yaml

@@ -389,7 +389,7 @@ services:
       `chatterbox`; the win is sub-second start for streaming consumers.
     category: tts
     version: 1
-    status: experimental
+    status: ready
     host: irv-ml1
     lifecycle:
       stack: chatterbox-fast
@@ -502,8 +502,8 @@ services:
       repetition_penalty 1.2). exaggeration / cfg_weight are deliberately omitted —
       Turbo ignores them. streamable:true routes the UI to an ephemeral audition
       (progressive <audio>, no Asset/library entry); re-run on `chatterbox` to keep
-      output. Status experimental until the first real browser audition verifies
+      output. Browser audition verified 2026-06-02 (progressive playback confirmed
-      progressive playback end-to-end.
+      end-to-end) — promoted to ready.
 
   - id: index-tts
     name: IndexTTS-2
@@ -1029,6 +1029,7 @@ services:
       with speaker switching. Not for low-latency single-line use.
     category: tts
     version: 3
+    status: down
     host: irv-ml1
     lifecycle:
       stack: vibevoice
@@ -1127,7 +1128,7 @@ services:
       stack: voxtral
       vram_gb: 12
       gpu_device_id: 1
-    endpoint: http://10.100.79.3:8197/v1/audio/speech
+    endpoint: http://10.100.79.3:8201/v1/audio/speech
     method: POST
     content_type: application/json
     model:
@@ -1147,7 +1148,7 @@ services:
       - name: voice
         type: select
         label: Voice
-        source_url: http://10.100.79.3:8197/v1/audio/voices
+        source_url: http://10.100.79.3:8201/v1/audio/voices
         default: neutral_female
         options:
           - neutral_female

stacks/voxtral/.env.example

@@ -15,7 +15,9 @@ VOXTRAL_MODEL=mistralai/Voxtral-4B-TTS-2603
 
 # ── network ──────────────────────────────────────────────────────────
 # Host port (container listens on 8000 internally).
-VOXTRAL_PORT=8197
+# Was 8197 — moved to 8201 (2026-06-02): 8197 is taken by the live
+# chatterbox-fast stack. Don't reuse 8197.
+VOXTRAL_PORT=8201
 VOXTRAL_BIND=0.0.0.0
 
 # ── runtime / GPU ────────────────────────────────────────────────────

stacks/voxtral/README.md

@@ -43,24 +43,24 @@ English; nothing else is multilingual at all).
 ## API
 
 vLLM-Omni serves an OpenAI-compatible API at
-`http://10.100.79.3:8197/v1`:
+`http://10.100.79.3:8201/v1`:
 
 ```bash
 # Single-shot synthesis.
-curl -fsS -X POST http://10.100.79.3:8197/v1/audio/speech \
+curl -fsS -X POST http://10.100.79.3:8201/v1/audio/speech \
   -H 'Content-Type: application/json' \
   -d '{"model":"mistralai/Voxtral-4B-TTS-2603","input":"Hello there.","voice":"alloy","response_format":"wav"}' \
   > out.wav
 
 # Streaming.
-curl -fsS -X POST http://10.100.79.3:8197/v1/audio/speech \
+curl -fsS -X POST http://10.100.79.3:8201/v1/audio/speech \
   -H 'Content-Type: application/json' \
   -d '{"model":"mistralai/Voxtral-4B-TTS-2603","input":"long passage…","voice":"alloy","stream":true}' \
   | mpv --no-cache -
 
 # vLLM-Omni standard endpoints.
-curl http://10.100.79.3:8197/v1/models    # confirms model loaded
+curl http://10.100.79.3:8201/v1/models    # confirms model loaded
-curl http://10.100.79.3:8197/v1/audio/voices  # built-in + cloned voices
+curl http://10.100.79.3:8201/v1/audio/voices  # built-in + cloned voices
 ```
 
 ## Deploy