update README.md

README.md

@@ -84,15 +84,12 @@ python test_model_12hz_base.py
 ```
 ### vllm
 #### 单机推理
-
-启动服务
+VoiceDesign
 ```bash
-#以VoiceDesign为例子，CustomVoice和Voice Clone需要使用不同的模型
+## serve启动
 VLLM_USE_V1=0  python -m vllm.entrypoints.openai.api_server --model Qwen3-TTS/Qwen3-TTS-12Hz-1.7B-VoiceDesign --served-model-name qwen3-tts --host 0.0.0.0 --port 8000 --trust-remote-code --dtype bfloat16 --disable-async-output-proc
-```
-调用服务：
-```
-VoiceDesign
+
+## client访问
 curl -sS http://127.0.0.1:8000/v1/audio/speech \
   -H "Content-Type: application/json" \
   -o output.wav \
@@ -111,8 +108,14 @@ curl -sS http://127.0.0.1:8000/v1/audio/speech \
     },
     "response_format":"wav"
   }'
+```
 
 CustomVoice
+```bash
+## serve启动
+VLLM_USE_V1=0  python -m vllm.entrypoints.openai.api_server --model Qwen3-TTS/Qwen3-TTS-12Hz-1.7B-CustomVoice --served-model-name qwen3-tts --host 0.0.0.0 --port 8000 --trust-remote-code --dtype bfloat16 --disable-async-output-proc
+
+## client访问
 curl -sS http://127.0.0.1:8000/v1/audio/speech \
   -H "Content-Type: application/json" \
   -o output_customvoice.wav \
@@ -132,8 +135,14 @@ curl -sS http://127.0.0.1:8000/v1/audio/speech \
     },
     "response_format":"wav"
   }'
+```
 
 Voice Clone
+```bash
+## serve启动
+VLLM_USE_V1=0  python -m vllm.entrypoints.openai.api_server --model Qwen3-TTS/Qwen3-TTS-12Hz-1.7B-Base --served-model-name qwen3-tts --host 0.0.0.0 --port 8000 --trust-remote-code --dtype bfloat16 --disable-async-output-proc
+
+## client访问
 curl -sS http://127.0.0.1:8000/v1/audio/speech \
   -H "Content-Type: application/json" \
   -o output_clone_icl.wav \