Merge branch 'main' into add_news

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

@@ -1,5 +1,4 @@
 import json
-from config.logger import setup_logging
 from core.handle.sendAudioHandle import send_stt_message
 from core.utils.util import remove_punctuation_and_length
 import shutil
@@ -20,7 +19,16 @@ WAKEUP_CONFIG = {
 }
 
 
-async def handleHelloMessage(conn):
+async def handleHelloMessage(conn, msg_json):
+    """处理hello消息"""
+    audio_params = msg_json.get("audio_params")
+    if audio_params:
+        format = audio_params.get("format")
+        conn.logger.bind(tag=TAG).info(f"客户端音频格式: {format}")
+        conn.audio_format = format
+        conn.asr.set_audio_format(format)
+        conn.welcome_msg["audio_params"] = audio_params
+
     await conn.websocket.send(json.dumps(conn.welcome_msg))
 
 

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

@@ -5,7 +5,7 @@ from core.handle.sendAudioHandle import send_stt_message
 from core.handle.intentHandler import handle_user_intent
 from core.utils.output_counter import check_device_output_limit
 from core.handle.ttsReportHandle import enqueue_tts_report
-from core.providers.tts.base import audio_to_opus_data
+from core.utils.util import audio_to_data
 
 TAG = __name__
 
@@ -111,7 +111,7 @@ async def max_out_size(conn):
     conn.tts_last_text_index = 0
     conn.llm_finish_task = True
     file_path = "config/assets/max_output_size.wav"
-    opus_packets, _ = audio_to_opus_data(file_path)
+    opus_packets, _ = audio_to_data(file_path)
     conn.audio_play_queue.put((opus_packets, text, 0))
     conn.close_after_chat = True
 
@@ -133,7 +133,7 @@ async def check_bind_device(conn):
 
         # 播放提示音
         music_path = "config/assets/bind_code.wav"
-        opus_packets, _ = audio_to_opus_data(music_path)
+        opus_packets, _ = audio_to_data(music_path)
         conn.audio_play_queue.put((opus_packets, text, 0))
 
         # 逐个播放数字
@@ -141,7 +141,7 @@ async def check_bind_device(conn):
             try:
                 digit = conn.bind_code[i]
                 num_path = f"config/assets/bind_code/{digit}.wav"
-                num_packets, _ = audio_to_opus_data(num_path)
+                num_packets, _ = audio_to_data(num_path)
                 conn.audio_play_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}")
@@ -153,5 +153,5 @@ async def check_bind_device(conn):
         conn.tts_last_text_index = 0
         conn.llm_finish_task = True
         music_path = "config/assets/bind_not_found.wav"
-        opus_packets, _ = audio_to_opus_data(music_path)
+        opus_packets, _ = audio_to_data(music_path)
         conn.audio_play_queue.put((opus_packets, text, 0))

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

@@ -115,7 +115,7 @@ 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"
             )
-            audios, duration = conn.tts.audio_to_opus_data(stop_tts_notify_voice)
+            audios, _ = conn.tts.audio_to_opus_data(stop_tts_notify_voice)
             await sendAudio(conn, audios)
         # 清除服务端讲话状态
         conn.clearSpeakStatus()

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

@@ -20,7 +20,7 @@ async def handleTextMessage(conn, message):
             await conn.websocket.send(message)
             return
         if msg_json["type"] == "hello":
-            await handleHelloMessage(conn)
+            await handleHelloMessage(conn, msg_json)
         elif msg_json["type"] == "abort":
             await handleAbortMessage(conn)
         elif msg_json["type"] == "listen":