Merge branch 'py_test_end' into fix-end

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

@@ -33,6 +33,7 @@ class TTSProvider(TTSProviderBase):
         self.api_key = config.get("api_key")
         if not self.api_key:
             raise ValueError("api_key is required for CosyVoice TTS")
+        self.report_on_last = True
 
         # WebSocket配置
         self.ws_url = "wss://dashscope.aliyuncs.com/api-ws/v1/inference/"

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

@@ -104,6 +104,7 @@ class TTSProvider(TTSProviderBase):
         self.access_key_secret = config.get("access_key_secret")
         self.appkey = config.get("appkey")
         self.format = config.get("format", "pcm")
+        self.report_on_last = True
 
         # 音色配置 - CosyVoice大模型音色
         if config.get("private_voice"):

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

@@ -41,6 +41,7 @@ class TTSProviderBase(ABC):
         self.tts_audio_queue = queue.Queue()
         self.tts_audio_first_sentence = True
         self.before_stop_play_files = []
+        self.report_on_last = False
 
         self.tts_text_buff = []
         self.punctuations = (
@@ -323,7 +324,7 @@ class TTSProviderBase(ABC):
     def _audio_play_priority_thread(self):
         # 需要上报的文本和音频列表
         enqueue_text = None
-        enqueue_audio = None
+        enqueue_audio = []
         while not self.conn.stop_event.is_set():
             text = None
             try:
@@ -343,14 +344,24 @@ class TTSProviderBase(ABC):
 
                 # 收到下一个文本开始或会话结束时进行上报
                 if sentence_type is not SentenceType.MIDDLE:
-                    # 上报TTS数据
-                    if enqueue_text is not None and enqueue_audio is not None:
-                        enqueue_tts_report(self.conn, enqueue_text, enqueue_audio)
-                    enqueue_audio = []
-                    enqueue_text = text
+                    if self.report_on_last:
+                        # 累积模式：适用于全程只有一个语音流的TTS（如seed-tts-2.0）
+                        # FIRST时只记录文本，音频持续累积，仅在LAST时统一上报
+                        if text:
+                            enqueue_text = text
+                        if sentence_type == SentenceType.LAST:
+                            enqueue_tts_report(self.conn, enqueue_text, enqueue_audio)
+                            enqueue_audio = []
+                            enqueue_text = None
+                    else:
+                        # 非累积模式：每个句子分别上报
+                        if enqueue_text is not None:
+                            enqueue_tts_report(self.conn, enqueue_text, enqueue_audio)
+                        enqueue_audio = []
+                        enqueue_text = text
 
                 # 收集上报音频数据
-                if isinstance(audio_datas, bytes) and enqueue_audio is not None:
+                if isinstance(audio_datas, bytes):
                     enqueue_audio.append(audio_datas)
 
                 # 发送音频

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

@@ -148,6 +148,8 @@ 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.report_on_last = self.resource_type
         self.activate_session = False
         if config.get("private_voice"):
             self.voice = config.get("private_voice")
@@ -511,7 +513,7 @@ 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 +524,17 @@ 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～～")

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

@@ -76,6 +76,7 @@ class TTSProvider(TTSProviderBase):
         self.app_id = config.get("app_id")
         self.api_key = config.get("api_key")
         self.api_secret = config.get("api_secret")
+        self.report_on_last = True
 
         # 接口地址
         self.api_url = config.get("api_url", "wss://cbm01.cn-huabei-1.xf-yun.com/v1/private/mcd9m97e6")