update:移除阿里云即将下架的模型

README.md

@@ -214,8 +214,8 @@ Websocket接口地址: wss://2662r3426b.vicp.fun/xiaozhi/v1/
 |:---:|:---:|:---:|
 | ASR(语音识别) | FunASR(本地) | 👍XunfeiStreamASR(讯飞流式) |
 | LLM(大模型) | glm-4-flash(智谱) | 👍qwen-flash(阿里百炼) |
-| VLLM(视觉大模型) | glm-4v-flash(智谱) | 👍qwen2.5-vl-3b-instructh(阿里百炼) |
+| VLLM(视觉大模型) | glm-4v-flash(智谱) | 👍qwen3.5-flash(阿里百炼) |
-| TTS(语音合成) | ✅LinkeraiTTS(灵犀流式) | 👍HuoshanDoubleStreamTTS(火山流式) |
+| TTS(语音合成) | EdgeTTS(微软) | 👍HuoshanDoubleStreamTTS(火山流式) |
 | Intent(意图识别) | function_call(函数调用) | function_call(函数调用) |
 | Memory(记忆功能) | mem_local_short(本地短期记忆） | mem_local_short（本地短期记忆） |
 

README_de.md

@@ -212,8 +212,8 @@ Websocket-Schnittstellenadresse: wss://2662r3426b.vicp.fun/xiaozhi/v1/
 |:---:|:---:|:---:|
 | ASR (Spracherkennung) | FunASR (Lokal) | 👍XunfeiStreamASR (Xunfei-Streaming) |
 | LLM (Großes Modell) | glm-4-flash (Zhipu) | 👍qwen-flash (Alibaba Bailian) |
-| VLLM (Vision Large Model) | glm-4v-flash (Zhipu) | 👍qwen2.5-vl-3b-instructh (Alibaba Bailian) |
+| VLLM (Vision Large Model) | glm-4v-flash (Zhipu) | 👍qwen3.5-flash (Alibaba Bailian) |
-| TTS (Sprachsynthese) | ✅LinkeraiTTS (Lingxi-Streaming) | 👍HuoshanDoubleStreamTTS (Volcano-Streaming) |
+| TTS (Sprachsynthese) | EdgeTTS (Microsoft) | 👍HuoshanDoubleStreamTTS (Volcano-Streaming) |
 | Intent (Absichtserkennung) | function_call (Funktionsaufruf) | function_call (Funktionsaufruf) |
 | Memory (Gedächtnisfunktion) | mem_local_short (Lokales Kurzzeitgedächtnis) | mem_local_short (Lokales Kurzzeitgedächtnis) |
 

README_en.md

@@ -212,8 +212,8 @@ Websocket Interface Address: wss://2662r3426b.vicp.fun/xiaozhi/v1/
 |:---:|:---:|:---:|
 | ASR(Speech Recognition) | FunASR(Local) | 👍XunfeiStreamASR(Xunfei Streaming) |
 | LLM(Large Model) | glm-4-flash(Zhipu) | 👍qwen-flash(Alibaba Bailian) |
-| VLLM(Vision Large Model) | glm-4v-flash(Zhipu) | 👍qwen2.5-vl-3b-instructh(Alibaba Bailian) |
+| VLLM(Vision Large Model) | glm-4v-flash(Zhipu) | 👍qwen3.5-flash(Alibaba Bailian) |
-| TTS(Speech Synthesis) | ✅LinkeraiTTS(Lingxi streaming) | 👍HuoshanDoubleStreamTTS(Volcano Streaming) |
+| TTS(Speech Synthesis) | EdgeTTS(Microsoft) | 👍HuoshanDoubleStreamTTS(Volcano Streaming) |
 | Intent(Intent Recognition) | function_call(Function calling) | function_call(Function calling) |
 | Memory(Memory function) | mem_local_short(Local short-term memory) | mem_local_short(Local short-term memory) |
 

README_pt_BR.md

@@ -212,8 +212,8 @@ Endereço da Interface WebSocket: wss://2662r3426b.vicp.fun/xiaozhi/v1/
 |:---:|:---:|:---:|
 | ASR(Reconhecimento de Fala) | FunASR(Local) | 👍XunfeiStreamASR(Xunfei Streaming) |
 | LLM(Modelo de Linguagem) | glm-4-flash(Zhipu) | 👍qwen-flash(Alibaba Bailian) |
-| VLLM(Modelo de Visão) | glm-4v-flash(Zhipu) | 👍qwen2.5-vl-3b-instructh(Alibaba Bailian) |
+| VLLM(Modelo de Visão) | glm-4v-flash(Zhipu) | 👍qwen3.5-flash(Alibaba Bailian) |
-| TTS(Síntese de Voz) | ✅LinkeraiTTS(Lingxi streaming) | 👍HuoshanDoubleStreamTTS(Volcano Streaming) |
+| TTS(Síntese de Voz) | EdgeTTS(Microsoft) | 👍HuoshanDoubleStreamTTS(Volcano Streaming) |
 | Intent(Reconhecimento de Intenção) | function_call(Chamada de função) | function_call(Chamada de função) |
 | Memory(Função de Memória) | mem_local_short(Memória local de curto prazo) | mem_local_short(Memória local de curto prazo) |
 

README_vi.md

@@ -213,8 +213,8 @@ Công cụ kiểm tra dịch vụ: https://2662r3426b.vicp.fun/test/
 |:---:|:---:|:---:|
 | ASR(Nhận dạng giọng nói) | FunASR(Local) | 👍XunfeiStreamASR(Xunfei Streaming) |
 | LLM(Mô hình lớn) | glm-4-flash(Zhipu) | 👍qwen-flash(Alibaba Bailian) |
-| VLLM(Mô hình lớn thị giác) | glm-4v-flash(Zhipu) | 👍qwen2.5-vl-3b-instructh(Alibaba Bailian) |
+| VLLM(Mô hình lớn thị giác) | glm-4v-flash(Zhipu) | 👍qwen3.5-flash(Alibaba Bailian) |
-| TTS(Tổng hợp giọng nói) | ✅LinkeraiTTS(Lingxi streaming) | 👍HuoshanDoubleStreamTTS(Volcano Streaming) |
+| TTS(Tổng hợp giọng nói) | EdgeTTS(Microsoft) | 👍HuoshanDoubleStreamTTS(Volcano Streaming) |
 | Intent(Nhận dạng ý định) | function_call(Gọi hàm) | function_call(Gọi hàm) |
 | Memory(Chức năng bộ nhớ) | mem_local_short(Bộ nhớ ngắn hạn cục bộ) | mem_local_short(Bộ nhớ ngắn hạn cục bộ) |
 

docs/FAQ.md

@@ -40,8 +40,8 @@ conda install conda-forge::ffmpeg
 |:---:|:---:|:---:|
 | ASR(语音识别) | FunASR(本地) | 👍XunfeiStreamASR(讯飞流式) |
 | LLM(大模型) | glm-4-flash(智谱) | 👍qwen-flash(阿里百炼) |
-| VLLM(视觉大模型) | glm-4v-flash(智谱) | 👍qwen2.5-vl-3b-instructh(阿里百炼) |
+| VLLM(视觉大模型) | glm-4v-flash(智谱) | 👍qwen3.5-flash(阿里百炼) |
-| TTS(语音合成) | ✅LinkeraiTTS(灵犀流式) | 👍HuoshanDoubleStreamTTS(火山流式) |
+| TTS(语音合成) | EdgeTTS(微软) | 👍HuoshanDoubleStreamTTS(火山流式) |
 | Intent(意图识别) | function_call(函数调用) | function_call(函数调用) |
 | Memory(记忆功能) | mem_local_short(本地短期记忆） | mem_local_short（本地短期记忆） |
 

main/manager-api/src/main/resources/db/changelog/202604161357.sql

@@ -0,0 +1,17 @@
+-- 更新模型名称：qwen2.5-vl-3b-instruct 改为 qwen3.5-flash
+UPDATE `ai_model_config` 
+SET `config_json` = JSON_SET(`config_json`, '$.model_name', 'qwen3.5-flash')
+WHERE `id` = 'VLLM_QwenVLVLLM' 
+AND JSON_EXTRACT(`config_json`, '$.model_name') = 'qwen2.5-vl-3b-instruct';
+
+-- 更新模型名称：qwen-turbo 改为 qwen-flash
+UPDATE `ai_model_config` 
+SET `config_json` = JSON_SET(`config_json`, '$.model_name', 'qwen-flash')
+WHERE `id` = 'LLM_AliLLM' 
+AND JSON_EXTRACT(`config_json`, '$.model_name') = 'qwen-turbo';
+
+-- 更新备注：qwen-turbo 改为 qwen-flash
+UPDATE `ai_model_config` 
+SET `remark` = REPLACE(`remark`, 'qwen-turbo', 'qwen-flash')
+WHERE `id` = 'LLM_AliLLM' 
+AND `remark` LIKE '%qwen-turbo%';

main/manager-api/src/main/resources/db/changelog/db.changelog-master.yaml

@@ -605,4 +605,11 @@ databaseChangeLog:
       changes:
         - sqlFile:
             encoding: utf8
-            path: classpath:db/changelog/202604011545.sql
+            path: classpath:db/changelog/202604011545.sql
+  - changeSet:
+      id: 202604161357
+      author: hrz
+      changes:
+        - sqlFile:
+            encoding: utf8
+            path: classpath:db/changelog/202604161357.sql

main/xiaozhi-server/config.yaml

@@ -579,7 +579,7 @@ LLM:
     type: openai
     # 可在这里找到你的 api_key https://bailian.console.aliyun.com/?apiKey=1#/api-key
     base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-    model_name: qwen-turbo
+    model_name: qwen-flash
     api_key: 你的deepseek web key
     temperature: 0.7  # 温度值
     max_tokens: 500   # 最大生成token数
@@ -714,7 +714,7 @@ VLLM:
     api_key: 你的api_key
   QwenVLVLLM:
     type: openai
-    model_name: qwen2.5-vl-3b-instruct
+    model_name: qwen3.5-flash
     url: https://dashscope.aliyuncs.com/compatible-mode/v1
     # 可在这里找到你的api key https://bailian.console.aliyun.com/?apiKey=1#/api-key
     api_key: 你的api_key