Merge pull request #2995 from xinnan-tech/py_fix_HuoShanTTS

Py fix huo shan tts
2026-07-22 07:03:53 +08:00 · 2026-03-12 16:25:47 +08:00
parent 4f6cdc745f fbb0e02fdd
commit dd24dc0abc
8 changed files with 38 additions and 15 deletions
@@ -189,7 +189,7 @@ export default {
  'editVoiceDialog.remarkPlaceholder': '请输入备注内容',
  'editVoiceDialog.generatePreview': '生成试听',
  'editVoiceDialog.defaultVoiceName': '湾湾小何',
-  'editVoiceDialog.defaultLanguageType': '中文',
+  'editVoiceDialog.defaultLanguageType': '普通话',
  'editVoiceDialog.requiredVoiceCode': '请输入音色编码',
  'editVoiceDialog.requiredVoiceName': '请输入音色名称',

@@ -189,7 +189,7 @@ export default {
  'editVoiceDialog.remarkPlaceholder': '請輸入備註內容',
  'editVoiceDialog.generatePreview': '生成試聽',
  'editVoiceDialog.defaultVoiceName': '灣灣小何',
-  'editVoiceDialog.defaultLanguageType': '中文',
+  'editVoiceDialog.defaultLanguageType': '普通話',
  'editVoiceDialog.requiredVoiceCode': '請輸入音色編碼',
  'editVoiceDialog.requiredVoiceName': '請輸入音色名稱',

@@ -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
@@ -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/"
@@ -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"):
@@ -40,6 +40,7 @@ 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 = (
@@ -322,7 +323,7 @@ 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:
@@ -342,14 +343,24 @@ 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
@@ -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～～")
@@ -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")