Revert "feat: replace MeloTTS with Coqui XTTS-v2 natural Korean voice"

This reverts commit 39a0944105.

docker-compose.yml

@@ -66,15 +66,13 @@ services:
       WHISPER_MODEL: ${WHISPER_MODEL:-medium}
       WHISPER_DEVICE: ${WHISPER_DEVICE:-cuda}
       WHISPER_COMPUTE_TYPE: ${WHISPER_COMPUTE_TYPE:-float16}
-      # Coqui XTTS-v2 (natural female Korean voice, replaces MeloTTS) on the GPU
-      # (cu128 torch baked by docker/setup-xtts.sh). Set here WITH DEFAULTS so
-      # supervisord's %(ENV_XTTS_*)s passthrough always resolves and an .env
-      # override actually reaches the xtts-worker.
-      XTTS_DEVICE: ${XTTS_DEVICE:-cuda}
-      # Built-in studio speaker (female). Other options include "Daisy Studious",
-      # "Sofia Hellen", "Alma María", etc. — any XTTS-v2 studio speaker name.
-      XTTS_SPEAKER: ${XTTS_SPEAKER:-Ana Florence}
-      XTTS_LANGUAGE: ${XTTS_LANGUAGE:-ko}
+      # MeloTTS on the GPU (cu128 torch baked by docker/setup-melo.sh). CPU synth
+      # serialised under load and pushed TTS to 7-8s; GPU does ~0.3s/sentence.
+      MELO_DEVICE: ${MELO_DEVICE:-cuda}
+      # Speaking rate for MeloTTS. Set here (with a default) so supervisord's
+      # %(ENV_MELO_SPEED)s passthrough always resolves and an .env override
+      # actually reaches the melo-worker. Lower it (e.g. 1.1) for a calmer pace.
+      MELO_SPEED: ${MELO_SPEED:-1.5}
       # Optional single-language lock for replies (empty = user's own language).
       OUTPUT_LANGUAGE: ${OUTPUT_LANGUAGE:-ko}
       # Drop the pre-loop planner LLM call to cut voice-reply latency on small