[Bugfix][Qwen3TTS] Load speaker_id/voices from model configuration (#1079)

Signed-off-by: pablo <juanz9312@gmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: WeiQing Chen <40507679+david6666666@users.noreply.github.com>

examples/online_serving/qwen3_tts/README.md

@@ -75,6 +75,9 @@ curl -X POST http://localhost:8000/v1/audio/speech \
         "voice": "Vivian",
         "instructions": "Speak with great enthusiasm"
     }' --output excited.wav
+
+# List available voices in CustomVoice models
+curl http://localhost:8000/v1/audio/voices
 ```
 
 ## API Reference