diff --git a/stacks/qwen3-tts/compose.yaml b/stacks/qwen3-tts/compose.yaml
index ff02623..8589eee 100644
--- a/stacks/qwen3-tts/compose.yaml
+++ b/stacks/qwen3-tts/compose.yaml
@@ -52,6 +52,13 @@ services:
       - PORT=8880
       - TTS_BACKEND=${QWEN3_TTS_BACKEND:-official}
       - TTS_MODEL_NAME=${QWEN3_TTS_MODEL:-Qwen/Qwen3-TTS-12Hz-1.7B}
+      # Only used when TTS_BACKEND=optimized — points the optimized backend
+      # at the upstream config.yaml (which defines the model registry +
+      # default model). Without this, the optimized backend looks at
+      # ~/qwen3-tts/config.yaml inside the container, which doesn't exist
+      # at runtime, leaving the model registry empty and synthesis fails
+      # with "Unknown model key".
+      - TTS_CONFIG=/app/config.yaml
       - TTS_WARMUP_ON_START=${QWEN3_TTS_WARMUP:-true}
       - TTS_MAX_CONCURRENT=${QWEN3_TTS_MAX_CONCURRENT:-1}
       - ENABLE_VOICE_STUDIO=${QWEN3_TTS_VOICE_STUDIO:-true}