update:旧非流失兼容改造

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

@@ -44,9 +44,6 @@ async def checkWakeupWords(conn, text):
     _, filtered_text = remove_punctuation_and_length(text)
     if filtered_text in conn.config.get("wakeup_words"):
         await send_stt_message(conn, text)
-        conn.tts_first_text_index = 0
-        conn.tts_last_text_index = 0
-        conn.llm_finish_task = True
 
         file = getWakeupWordFile(WAKEUP_CONFIG["file_name"])
         if file is None:
@@ -56,7 +53,7 @@ async def checkWakeupWords(conn, text):
         text_hello = WAKEUP_CONFIG["text"]
         if not text_hello:
             text_hello = text
-        conn.tts.audio_play_queue.put((opus_packets, text_hello, 0))
+        conn.tts.tts_audio_queue.put((opus_packets, text_hello, 0))
         if time.time() - WAKEUP_CONFIG["create_time"] > WAKEUP_CONFIG["refresh_time"]:
             asyncio.create_task(wakeupWordsResponse(conn))
         return True
@@ -91,7 +88,7 @@ async def wakeupWordsResponse(conn):
     result = conn.llm.response_no_stream(conn.config["prompt"], wakeup_word)
     if result is None or result == "":
         return
-    tts_file = await asyncio.to_thread(conn.tts.to_tts, result, 0)
+    tts_file = await asyncio.to_thread(conn.tts.to_tts, result)
 
     if tts_file is not None and os.path.exists(tts_file):
         file_type = os.path.splitext(tts_file)[1]

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

@@ -4,6 +4,7 @@ import uuid
 from core.handle.sendAudioHandle import send_stt_message
 from core.handle.helloHandle import checkWakeupWords
 from core.utils.util import remove_punctuation_and_length
+from core.providers.tts.dto.dto import ContentType
 from core.utils.dialogue import Message
 from plugins_func.register import Action
 from loguru import logger
@@ -143,11 +144,4 @@ async def process_intent_result(conn, intent_result, original_text):
 
 
 def speak_txt(conn, text):
-    text_index = (
-        conn.tts_last_text_index + 1 if hasattr(conn, "tts_last_text_index") else 0
-    )
-    conn.recode_first_last_text(text, text_index)
-    future = conn.executor.submit(conn.speak_and_play, None, text, text_index)
-    conn.llm_finish_task = True
-    conn.tts_queue.put((future, text_index))
-    conn.dialogue.put(Message(role="assistant", content=text))
+    conn.tts.tts_one_sentence(conn, ContentType.TEXT, content_detail=text)

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

@@ -110,12 +110,9 @@ async def no_voice_close_connect(conn):
 async def max_out_size(conn):
     text = "不好意思，我现在有点事情要忙，明天这个时候我们再聊，约好了哦！明天不见不散，拜拜！"
     await send_stt_message(conn, text)
-    conn.tts_first_text_index = 0
-    conn.tts_last_text_index = 0
-    conn.llm_finish_task = True
     file_path = "config/assets/max_output_size.wav"
     opus_packets, _ = audio_to_data(file_path)
-    conn.tts.audio_play_queue.put((opus_packets, text, 0))
+    conn.tts.tts_audio_queue.put((opus_packets, text, 0))
     conn.close_after_chat = True
 
 
@@ -130,14 +127,11 @@ async def check_bind_device(conn):
 
         text = f"请登录控制面板，输入{conn.bind_code}，绑定设备。"
         await send_stt_message(conn, text)
-        conn.tts_first_text_index = 0
-        conn.tts_last_text_index = 6
-        conn.llm_finish_task = True
 
         # 播放提示音
         music_path = "config/assets/bind_code.wav"
         opus_packets, _ = audio_to_data(music_path)
-        conn.tts.audio_play_queue.put((opus_packets, text, 0))
+        conn.tts.tts_audio_queue.put((opus_packets, text, 0))
 
         # 逐个播放数字
         for i in range(6):  # 确保只播放6位数字
@@ -145,16 +139,13 @@ async def check_bind_device(conn):
                 digit = conn.bind_code[i]
                 num_path = f"config/assets/bind_code/{digit}.wav"
                 num_packets, _ = audio_to_data(num_path)
-                conn.tts.audio_play_queue.put((num_packets, None, i + 1))
+                conn.tts.tts_audio_queue.put((num_packets, None, i + 1))
             except Exception as e:
                 conn.logger.bind(tag=TAG).error(f"播放数字音频失败: {e}")
                 continue
     else:
         text = f"没有找到该设备的版本信息，请正确配置 OTA地址，然后重新编译固件。"
         await send_stt_message(conn, text)
-        conn.tts_first_text_index = 0
-        conn.tts_last_text_index = 0
-        conn.llm_finish_task = True
         music_path = "config/assets/bind_not_found.wav"
         opus_packets, _ = audio_to_data(music_path)
-        conn.tts.audio_play_queue.put((opus_packets, text, 0))
+        conn.tts.tts_audio_queue.put((opus_packets, text, 0))

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

@@ -1,6 +1,7 @@
 import json
 import asyncio
 import time
+from core.providers.tts.dto.dto import SentenceType
 from core.utils.util import get_string_no_punctuation_or_emoji, analyze_emotion
 
 TAG = __name__
@@ -30,7 +31,7 @@ emoji_map = {
 }
 
 
-async def sendAudioMessage(conn, audios, text, text_index=0):
+async def sendAudioMessage(conn, sentenceType, audios, text):
     # 发送句子开始消息
     if text is not None:
         emotion = analyze_emotion(text)
@@ -46,25 +47,24 @@ async def sendAudioMessage(conn, audios, text, text_index=0):
             )
         )
 
-    if text_index == conn.tts_first_text_index:
-        conn.logger.bind(tag=TAG).info(f"发送第一段语音: {text}")
     await send_tts_message(conn, "sentence_start", text)
 
-    is_first_audio = text_index == conn.tts_first_text_index
-    await sendAudio(conn, audios, pre_buffer=is_first_audio)
+    await sendAudio(conn, audios, True)
 
     await send_tts_message(conn, "sentence_end", text)
 
     # 发送结束消息（如果是最后一个文本）
-    if conn.llm_finish_task and text_index == conn.tts_last_text_index:
+    if conn.llm_finish_task and sentenceType == SentenceType.LAST:
         await send_tts_message(conn, "stop", None)
-        await conn.tts.finish_session(conn.tts_session_id)
+        await conn.tts.finish_session(conn.sentence_id)
         if conn.close_after_chat:
             await conn.close()
 
 
 # 播放音频
 async def sendAudio(conn, audios, pre_buffer=True):
+    if audios is None or len(audios) == 0:
+        return
     # 流控参数优化
     frame_duration = 60  # 帧时长（毫秒），匹配 Opus 编码
     start_time = time.perf_counter()