fix: 修复选用seed-tts-2.0文本缺失

fix: 设备端说话状态与服务端同步

main/xiaozhi-server/core/handle/sendAudioHandle.py

@@ -21,7 +21,6 @@ async def sendAudioMessage(conn: "ConnectionHandler", sentenceType, audios, text
     if conn.tts.tts_audio_first_sentence:
         conn.logger.bind(tag=TAG).info(f"发送第一段语音: {text}")
         conn.tts.tts_audio_first_sentence = False
-        await send_tts_message(conn, "start", None)
 
     if sentenceType == SentenceType.FIRST:
         # 同一句子的后续消息加入流控队列，其他情况立即发送
@@ -204,7 +203,6 @@ def _start_background_sender(conn: "ConnectionHandler", rate_controller, flow_co
 
         conn.last_activity_time = time.time() * 1000
         await _do_send_audio(conn, packet, flow_control)
-        conn.client_is_speaking = True
 
     # 使用 start_sending 启动后台循环
     rate_controller.start_sending(send_callback)
@@ -232,12 +230,10 @@ async def _send_audio_with_rate_control(
         # 预缓冲：前N个包直接发送
         if flow_control["packet_count"] < PRE_BUFFER_COUNT:
             await _do_send_audio(conn, packet, flow_control)
-            conn.client_is_speaking = True
         elif send_delay > 0:
             # 固定延迟模式
             await asyncio.sleep(send_delay)
             await _do_send_audio(conn, packet, flow_control)
-            conn.client_is_speaking = True
         else:
             # 动态流控模式：仅添加到队列，由后台循环负责发送
             rate_controller.add_audio(packet)
@@ -318,3 +314,5 @@ async def send_stt_message(conn: "ConnectionHandler", text):
         json.dumps({"type": "stt", "text": stt_text, "session_id": conn.session_id})
     )
     await send_tts_message(conn, "start")
+    # 发送start消息后客户端状态会处于说话中状态，同步服务端状态
+    conn.client_is_speaking = True

main/xiaozhi-server/core/providers/tts/huoshan_double_stream.py

@@ -148,6 +148,7 @@ class TTSProvider(TTSProviderBase):
         self.access_token = config.get("access_token")
         self.cluster = config.get("cluster")
         self.resource_id = config.get("resource_id")
+        self.resource_type = True if self.resource_id == "seed-tts-2.0" else False
         self.activate_session = False
         if config.get("private_voice"):
             self.voice = config.get("private_voice")
@@ -511,7 +512,7 @@ class TTSProvider(TTSProviderBase):
                     if res.optional.event == EVENT_SessionCanceled:
                         logger.bind(tag=TAG).debug(f"释放服务端资源成功～～")
                         self.activate_session = False
-                    elif res.optional.event == EVENT_TTSSentenceStart:
+                    elif not self.resource_type and res.optional.event == EVENT_TTSSentenceStart:
                         json_data = json.loads(res.payload.decode("utf-8"))
                         self.tts_text = json_data.get("text", "")
                         logger.bind(tag=TAG).debug(f"句子语音生成开始: {self.tts_text}")
@@ -522,8 +523,17 @@ class TTSProvider(TTSProviderBase):
                         res.optional.event == EVENT_TTSResponse
                         and res.header.message_type == AUDIO_ONLY_RESPONSE
                     ):
+                        # 处理seed-tts-2.0文本字幕
+                        if self.resource_type and self.conn.tts_MessageText:
+                            logger.bind(tag=TAG).info(
+                                f"句子语音生成成功： {self.conn.tts_MessageText}"
+                            )
+                            self.tts_audio_queue.put(
+                                (SentenceType.FIRST, [], self.conn.tts_MessageText)
+                            )
+                            self.conn.tts_MessageText = None
                         self.wav_to_opus_data_audio_raw_stream(res.payload, callback=self.handle_opus)
-                    elif res.optional.event == EVENT_TTSSentenceEnd:
+                    elif not self.resource_type and res.optional.event == EVENT_TTSSentenceEnd:
                         logger.bind(tag=TAG).info(f"句子语音生成成功：{self.tts_text}")
                     elif res.optional.event == EVENT_SessionFinished:
                         logger.bind(tag=TAG).debug(f"会话结束～～")