update:优化音频播放

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

@@ -10,6 +10,8 @@ from abc import ABC, abstractmethod
 from config.logger import setup_logging
 from core.utils.util import audio_to_data
 from core.utils.tts import MarkdownCleaner
+from core.utils.output_counter import add_device_output
+from core.handle.reportHandle import enqueue_tts_report
 from core.handle.sendAudioHandle import sendAudioMessage
 from core.providers.tts.dto.dto import TTSMessageDTO, SentenceType, ContentType
 
@@ -226,6 +228,9 @@ class TTSProviderBase(ABC):
                     self.conn.loop,
                 )
                 future.result()
+                if self.conn.max_output_size > 0 and text:
+                    add_device_output(self.conn.headers.get("device-id"), len(text))
+                enqueue_tts_report(self.conn, text, audio_datas)
             except Exception as e:
                 logger.bind(tag=TAG).error(
                     f"audio_play_priority priority_thread: {text} {e}"
@@ -298,6 +303,14 @@ class TTSProviderBase(ABC):
             audio_datas, _ = self.audio_to_pcm_data(tts_file)
         else:
             audio_datas, _ = self.audio_to_opus_data(tts_file)
+
+        if (
+            self.delete_audio_file
+            and tts_file is not None
+            and os.path.exists(tts_file)
+            and tts_file.startswith(self.output_file)
+        ):
+            os.remove(tts_file)
         return audio_datas
 
     def _process_remaining_text(self):

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

@@ -1,3 +1,4 @@
+import os
 import asyncio
 import threading
 import traceback
@@ -149,7 +150,7 @@ class TTSProvider(TTSProviderBase):
         self.start_connection_flag = False
         self.tts_text = ""
         # 合成文字语音后，播放的音频文件列表
-        self.tts_audio_files = []
+        self.before_stop_play_files = []
         self.opus_encoder = opus_encoder_utils.OpusEncoderUtils(
             sample_rate=16000, channels=1, frame_size_ms=60
         )
@@ -188,6 +189,7 @@ class TTSProvider(TTSProviderBase):
                     )
                     future.result()
                     self.tts_audio_first_sentence = True
+                    self.before_stop_play_files.clear()
                 elif ContentType.TEXT == message.content_type:
                     if message.content_detail:
                         future = asyncio.run_coroutine_threadsafe(
@@ -196,9 +198,18 @@ class TTSProvider(TTSProviderBase):
                         )
                         future.result()
                 elif ContentType.FILE == message.content_type:
-                    pass
+                    self.before_stop_play_files.append(
+                        (message.content_file, message.content_detail)
+                    )
 
                 if message.sentence_type == SentenceType.LAST:
+                    for tts_file, text in self.before_stop_play_files:
+                        if tts_file and os.path.exists(tts_file):
+                            audio_datas = self._process_audio_file(tts_file)
+                            self.tts_audio_queue.put(
+                                (message.sentence_type, audio_datas, text)
+                            )
+                    self.before_stop_play_files.clear()
                     future = asyncio.run_coroutine_threadsafe(
                         self.finish_session(self.conn.sentence_id), loop=self.conn.loop
                     )