fix: 优化

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

@@ -3,7 +3,7 @@ import json
 import random
 import asyncio
 from core.utils.dialogue import Message
-from core.utils.util import audio_to_data_stream
+from core.utils.util import audio_to_data
 from core.providers.tts.dto.dto import SentenceType
 from core.utils.wakeup_word import WakeupWordsConfig
 from core.handle.sendAudioHandle import sendAudioMessage, send_stt_message
@@ -91,12 +91,7 @@ async def checkWakeupWords(conn, text):
         }
 
     # 获取音频数据
-    opus_packets = []
-    def handle_audio_frame(frame_data):
-        opus_packets.append(frame_data)
-
-    audio_to_data_stream(response.get("file_path"), is_opus=True, callback=handle_audio_frame)
-
+    opus_packets = audio_to_data(response.get("file_path"))
     # 播放唤醒词回复
     conn.client_abort = False
 

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

@@ -2,7 +2,7 @@ import json
 import time
 import asyncio
 from core.utils import textUtils
-from core.utils.util import audio_to_data_stream
+from core.utils.util import audio_to_data
 from core.providers.tts.dto.dto import SentenceType
 
 TAG = __name__
@@ -120,12 +120,7 @@ async def send_tts_message(conn, state, text=None):
             stop_tts_notify_voice = conn.config.get(
                 "stop_tts_notify_voice", "config/assets/tts_notify.mp3"
             )
-            # 获取音频数据
-            audios = []
-            def handle_audio_frame(frame_data):
-                audios.append(frame_data)
-
-            audio_to_data_stream(stop_tts_notify_voice, is_opus=True, callback=handle_audio_frame)
+            audios = audio_to_data(stop_tts_notify_voice, is_opus=True)
             await sendAudio(conn, audios)
         # 清除服务端讲话状态
         conn.clearSpeakStatus()

main/xiaozhi-server/core/utils/util.py

@@ -230,6 +230,56 @@ def audio_to_data_stream(audio_file_path, is_opus=True, callback: Callable[[Any]
     raw_data = audio.raw_data
     pcm_to_data_stream(raw_data, is_opus, callback)
 
+def audio_to_data(audio_file_path: str, is_opus: bool = True) -> list[bytes]:
+    """
+    将音频文件转换为Opus/PCM编码的帧列表
+    Args:
+        audio_file_path: 音频文件路径
+        is_opus: 是否进行Opus编码
+    """
+    # 获取文件后缀名
+    file_type = os.path.splitext(audio_file_path)[1]
+    if file_type:
+        file_type = file_type.lstrip(".")
+    # 读取音频文件，-nostdin 参数：不要从标准输入读取数据，否则FFmpeg会阻塞
+    audio = AudioSegment.from_file(
+        audio_file_path, format=file_type, parameters=["-nostdin"]
+    )
+
+    # 转换为单声道/16kHz采样率/16位小端编码（确保与编码器匹配）
+    audio = audio.set_channels(1).set_frame_rate(16000).set_sample_width(2)
+
+    # 获取原始PCM数据（16位小端）
+    raw_data = audio.raw_data
+
+    # 初始化Opus编码器
+    encoder = opuslib_next.Encoder(16000, 1, opuslib_next.APPLICATION_AUDIO)
+
+    # 编码参数
+    frame_duration = 60  # 60ms per frame
+    frame_size = int(16000 * frame_duration / 1000)  # 960 samples/frame
+
+    datas = []
+    # 按帧处理所有音频数据（包括最后一帧可能补零）
+    for i in range(0, len(raw_data), frame_size * 2):  # 16bit=2bytes/sample
+        # 获取当前帧的二进制数据
+        chunk = raw_data[i : i + frame_size * 2]
+
+        # 如果最后一帧不足，补零
+        if len(chunk) < frame_size * 2:
+            chunk += b"\x00" * (frame_size * 2 - len(chunk))
+
+        if is_opus:
+            # 转换为numpy数组处理
+            np_frame = np.frombuffer(chunk, dtype=np.int16)
+            # 编码Opus数据
+            frame_data = encoder.encode(np_frame.tobytes(), frame_size)
+        else:
+            frame_data = chunk if isinstance(chunk, bytes) else bytes(chunk)
+
+        datas.append(frame_data)
+
+    return datas
 
 def audio_bytes_to_data_stream(audio_bytes, file_type, is_opus, callback: Callable[[Any], Any]) -> None:
     """