update:优化未绑定用户的连接

main/xiaozhi-server/core/connection.py

@@ -151,11 +151,9 @@ class ConnectionHandler:
                     self.headers["device-id"] = query_params["device-id"][0]
                     self.headers["client-id"] = query_params["client-id"][0]
                 else:
-                    self.logger.bind(tag=TAG).error(
+                    await ws.send("端口正常，如需测试连接，请使用test_page.html")
-                        "无法从请求头和URL查询参数中获取device-id"
+                    await self.close(ws)
-                    )
                     return
-
             # 获取客户端ip地址
             self.client_ip = ws.remote_address[0]
             self.logger.bind(tag=TAG).info(
@@ -212,7 +210,8 @@ class ConnectionHandler:
     async def _save_and_close(self, ws):
         """保存记忆并关闭连接"""
         try:
-            await self.memory.save_memory(self.dialogue.dialogue)
+            if self.memory:
+                await self.memory.save_memory(self.dialogue.dialogue)
         except Exception as e:
             self.logger.bind(tag=TAG).error(f"保存记忆失败: {e}")
         finally:
@@ -318,7 +317,7 @@ class ConnectionHandler:
 
     def _init_report_threads(self):
         """初始化ASR和TTS上报线程"""
-        if not self.read_config_from_api:
+        if not self.read_config_from_api or self.need_bind:
             return
         if self.tts_report_thread is None or not self.tts_report_thread.is_alive():
             self.tts_report_thread = threading.Thread(

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

@@ -44,7 +44,7 @@ async def checkWakeupWords(conn, text):
         if file is None:
             asyncio.create_task(wakeupWordsResponse(conn))
             return False
-        opus_packets, duration = conn.tts.audio_to_opus_data(file)
+        opus_packets, _ = conn.tts.audio_to_opus_data(file)
         text_hello = WAKEUP_CONFIG["text"]
         if not text_hello:
             text_hello = text

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

@@ -6,6 +6,7 @@ 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
 
 TAG = __name__
 logger = setup_logging()
@@ -110,7 +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, _ = conn.tts.audio_to_opus_data(file_path)
+    opus_packets, _ = audio_to_opus_data(file_path)
     conn.audio_play_queue.put((opus_packets, text, 0))
     conn.close_after_chat = True
 
@@ -132,7 +133,7 @@ async def check_bind_device(conn):
 
         # 播放提示音
         music_path = "config/assets/bind_code.wav"
-        opus_packets, _ = conn.tts.audio_to_opus_data(music_path)
+        opus_packets, _ = audio_to_opus_data(music_path)
         conn.audio_play_queue.put((opus_packets, text, 0))
 
         # 逐个播放数字
@@ -140,7 +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, _ = conn.tts.audio_to_opus_data(num_path)
+                num_packets, _ = audio_to_opus_data(num_path)
                 conn.audio_play_queue.put((num_packets, None, i + 1))
             except Exception as e:
                 logger.bind(tag=TAG).error(f"播放数字音频失败: {e}")
@@ -152,5 +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, _ = conn.tts.audio_to_opus_data(music_path)
+        opus_packets, _ = audio_to_opus_data(music_path)
         conn.audio_play_queue.put((opus_packets, text, 0))

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

@@ -95,7 +95,7 @@ def opus_to_wav(opus_data):
 
 
 def enqueue_tts_report(conn, type, text, opus_data):
-    if not conn.read_config_from_api:
+    if not conn.read_config_from_api or conn.need_bind:
         return
     """将TTS数据加入上报队列
 
@@ -108,7 +108,7 @@ def enqueue_tts_report(conn, type, text, opus_data):
         # 使用连接对象的队列，传入文本和二进制数据而非文件路径
         conn.tts_report_queue.put((type, text, opus_data))
 
-        logger.bind(tag=TAG).info(
+        logger.bind(tag=TAG).debug(
             f"TTS数据已加入上报队列: {conn.device_id}, 音频大小: {len(opus_data)} "
         )
     except Exception as e:

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

@@ -1,11 +1,9 @@
 import asyncio
 from config.logger import setup_logging
 import os
-import numpy as np
-import opuslib_next
-from pydub import AudioSegment
 from abc import ABC, abstractmethod
 from core.utils.tts import MarkdownCleaner
+from core.utils.util import audio_to_opus_data
 
 TAG = __name__
 logger = setup_logging()
@@ -29,7 +27,9 @@ class TTSProviderBase(ABC):
                 try:
                     asyncio.run(self.text_to_speak(text, tmp_file))
                 except Exception as e:
-                    logger.bind(tag=TAG).warning(f"语音生成失败{5 - max_repeat_time + 1}次: {text}，错误: {e}")
+                    logger.bind(tag=TAG).warning(
+                        f"语音生成失败{5 - max_repeat_time + 1}次: {text}，错误: {e}"
+                    )
                     # 未执行成功，删除文件
                     if os.path.exists(tmp_file):
                         os.remove(tmp_file)
@@ -54,47 +54,4 @@ class TTSProviderBase(ABC):
         pass
 
     def audio_to_opus_data(self, audio_file_path):
-        """音频文件转换为Opus编码"""
+        return audio_to_opus_data(audio_file_path)
-        # 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)
-
-        # 音频时长(秒)
-        duration = len(audio) / 1000.0
-
-        # 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
-
-        opus_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))
-
-            # 转换为numpy数组处理
-            np_frame = np.frombuffer(chunk, dtype=np.int16)
-
-            # 编码Opus数据
-            opus_data = encoder.encode(np_frame.tobytes(), frame_size)
-            opus_datas.append(opus_data)
-
-        return opus_datas, duration

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

@@ -2,35 +2,40 @@ import json
 import socket
 import subprocess
 import re
+import os
+import numpy as np
 import requests
+import opuslib_next
+from pydub import AudioSegment
 from typing import Dict, Any
 from core.utils import tts, llm, intent, memory, vad, asr
 
 TAG = __name__
 emoji_map = {
-    'neutral': '😶',
+    "neutral": "😶",
-    'happy': '🙂',
+    "happy": "🙂",
-    'laughing': '😆',
+    "laughing": "😆",
-    'funny': '😂',
+    "funny": "😂",
-    'sad': '😔',
+    "sad": "😔",
-    'angry': '😠',
+    "angry": "😠",
-    'crying': '😭',
+    "crying": "😭",
-    'loving': '😍',
+    "loving": "😍",
-    'embarrassed': '😳',
+    "embarrassed": "😳",
-    'surprised': '😲',
+    "surprised": "😲",
-    'shocked': '😱',
+    "shocked": "😱",
-    'thinking': '🤔',
+    "thinking": "🤔",
-    'winking': '😉',
+    "winking": "😉",
-    'cool': '😎',
+    "cool": "😎",
-    'relaxed': '😌',
+    "relaxed": "😌",
-    'delicious': '🤤',
+    "delicious": "🤤",
-    'kissy': '😘',
+    "kissy": "😘",
-    'confident': '😏',
+    "confident": "😏",
-    'sleepy': '😴',
+    "sleepy": "😴",
-    'silly': '😜',
+    "silly": "😜",
-    'confused': '🙄'
+    "confused": "🙄",
 }
 
+
 def get_local_ip():
     try:
         s = socket.socket(socket.AF_INET, socket.SOCK_DGRAM)
@@ -117,9 +122,9 @@ def is_punctuation_or_emoji(char):
         "、",  # 中文顿号
         "“",
         "”",
-        "\"",  # 中文双引号 + 英文引号
+        '"',  # 中文双引号 + 英文引号
         "：",
-        ":",   # 中文冒号 + 英文冒号
+        ":",  # 中文冒号 + 英文冒号
     }
     if char.isspace() or char in punctuation_set:
         return True
@@ -353,12 +358,13 @@ def initialize_modules(
 
     return modules
 
+
 def analyze_emotion(text):
     """
     分析文本情感并返回对应的emoji名称（支持中英文）
     """
     if not text or not isinstance(text, str):
-        return 'neutral'
+        return "neutral"
 
     original_text = text
     text = text.lower().strip()
@@ -369,84 +375,444 @@ def analyze_emotion(text):
             return emotion
 
     # 标点符号分析
-    has_exclamation = '!' in original_text or '！' in original_text
+    has_exclamation = "!" in original_text or "！" in original_text
-    has_question = '?' in original_text or '？' in original_text
+    has_question = "?" in original_text or "？" in original_text
-    has_ellipsis = '...' in original_text or '…' in original_text
+    has_ellipsis = "..." in original_text or "…" in original_text
 
     # 定义情感关键词映射（中英文扩展版）
     emotion_keywords = {
-        'happy': ['开心', '高兴', '快乐', '愉快', '幸福', '满意', '棒', '好', '不错', '完美', '棒极了', '太好了',
+        "happy": [
-                  '好呀', '好的', 'happy', 'joy', 'great', 'good', 'nice', 'awesome', 'fantastic', 'wonderful'],
+            "开心",
-        'laughing': ['哈哈', '哈哈哈', '呵呵', '嘿嘿', '嘻嘻', '笑死', '太好笑了', '笑死我了', 'lol', 'lmao', 'haha',
+            "高兴",
-                     'hahaha', 'hehe', 'rofl', 'funny', 'laugh'],
+            "快乐",
-        'funny': ['搞笑', '滑稽', '逗', '幽默', '笑点', '段子', '笑话', '太逗了', 'hilarious', 'joke', 'comedy'],
+            "愉快",
-        'sad': ['伤心', '难过', '悲哀', '悲伤', '忧郁', '郁闷', '沮丧', '失望', '想哭', '难受', '不开心', '唉', '呜呜',
+            "幸福",
-                'sad', 'upset', 'unhappy', 'depressed', 'sorrow', 'gloomy'],
+            "满意",
-        'angry': ['生气', '愤怒', '气死', '讨厌', '烦人', '可恶', '烦死了', '恼火', '暴躁', '火大', '愤怒', '气炸了',
+            "棒",
-                  'angry', 'mad', 'annoyed', 'furious', 'pissed', 'hate'],
+            "好",
-        'crying': ['哭泣', '泪流', '大哭', '伤心欲绝', '泪目', '流泪', '哭死', '哭晕', '想哭', '泪崩',
+            "不错",
-                   'cry', 'crying', 'tears', 'sob', 'weep'],
+            "完美",
-        'loving': ['爱你', '喜欢', '爱', '亲爱的', '宝贝', '么么哒', '抱抱', '想你', '思念', '最爱', '亲亲', '喜欢你',
+            "棒极了",
-                   'love', 'like', 'adore', 'darling', 'sweetie', 'honey', 'miss you', 'heart'],
+            "太好了",
-        'embarrassed': ['尴尬', '不好意思', '害羞', '脸红', '难为情', '社死', '丢脸', '出丑',
+            "好呀",
-                        'embarrassed', 'awkward', 'shy', 'blush'],
+            "好的",
-        'surprised': ['惊讶', '吃惊', '天啊', '哇塞', '哇', '居然', '竟然', '没想到', '出乎意料',
+            "happy",
-                      'surprise', 'wow', 'omg', 'oh my god', 'amazing', 'unbelievable'],
+            "joy",
-        'shocked': ['震惊', '吓到', '惊呆了', '不敢相信', '震撼', '吓死', '恐怖', '害怕', '吓人',
+            "great",
-                    'shocked', 'shocking', 'scared', 'frightened', 'terrified', 'horror'],
+            "good",
-        'thinking': ['思考', '考虑', '想一下', '琢磨', '沉思', '冥想', '想', '思考中', '在想',
+            "nice",
-                      'think', 'thinking', 'consider', 'ponder', 'meditate'],
+            "awesome",
-        'winking': ['调皮', '眨眼', '你懂的', '坏笑', '邪恶', '奸笑', '使眼色',
+            "fantastic",
-                    'wink', 'teasing', 'naughty', 'mischievous'],
+            "wonderful",
-        'cool': ['酷', '帅', '厉害', '棒极了', '真棒', '牛逼', '强', '优秀', '杰出', '出色', '完美',
+        ],
-                 'cool', 'awesome', 'amazing', 'great', 'impressive', 'perfect'],
+        "laughing": [
-        'relaxed': ['放松', '舒服', '惬意', '悠闲', '轻松', '舒适', '安逸', '自在',
+            "哈哈",
-                     'relax', 'relaxed', 'comfortable', 'cozy', 'chill', 'peaceful'],
+            "哈哈哈",
-        'delicious': ['好吃', '美味', '香', '馋', '可口', '香甜', '大餐', '大快朵颐', '流口水', '垂涎',
+            "呵呵",
-                      'delicious', 'yummy', 'tasty', 'yum', 'appetizing', 'mouthwatering'],
+            "嘿嘿",
-        'kissy': ['亲亲', '么么', '吻', 'mua', 'muah', '亲一下', '飞吻',
+            "嘻嘻",
-                  'kiss', 'xoxo', 'hug', 'muah', 'smooch'],
+            "笑死",
-        'confident': ['自信', '肯定', '确定', '毫无疑问', '当然', '必须的', '毫无疑问', '确信', '坚信',
+            "太好笑了",
-                      'confident', 'sure', 'certain', 'definitely', 'positive'],
+            "笑死我了",
-        'sleepy': ['困', '睡觉', '晚安', '想睡', '好累', '疲惫', '疲倦', '困了', '想休息', '睡意',
+            "lol",
-                   'sleep', 'sleepy', 'tired', 'exhausted', 'bedtime', 'good night'],
+            "lmao",
-        'silly': ['傻', '笨', '呆', '憨', '蠢', '二', '憨憨', '傻乎乎', '呆萌',
+            "haha",
-                  'silly', 'stupid', 'dumb', 'foolish', 'goofy', 'ridiculous'],
+            "hahaha",
-        'confused': ['疑惑', '不明白', '不懂', '困惑', '疑问', '为什么', '怎么回事', '啥意思', '不清楚',
+            "hehe",
-                     'confused', 'puzzled', 'doubt', 'question', 'what', 'why', 'how']
+            "rofl",
+            "funny",
+            "laugh",
+        ],
+        "funny": [
+            "搞笑",
+            "滑稽",
+            "逗",
+            "幽默",
+            "笑点",
+            "段子",
+            "笑话",
+            "太逗了",
+            "hilarious",
+            "joke",
+            "comedy",
+        ],
+        "sad": [
+            "伤心",
+            "难过",
+            "悲哀",
+            "悲伤",
+            "忧郁",
+            "郁闷",
+            "沮丧",
+            "失望",
+            "想哭",
+            "难受",
+            "不开心",
+            "唉",
+            "呜呜",
+            "sad",
+            "upset",
+            "unhappy",
+            "depressed",
+            "sorrow",
+            "gloomy",
+        ],
+        "angry": [
+            "生气",
+            "愤怒",
+            "气死",
+            "讨厌",
+            "烦人",
+            "可恶",
+            "烦死了",
+            "恼火",
+            "暴躁",
+            "火大",
+            "愤怒",
+            "气炸了",
+            "angry",
+            "mad",
+            "annoyed",
+            "furious",
+            "pissed",
+            "hate",
+        ],
+        "crying": [
+            "哭泣",
+            "泪流",
+            "大哭",
+            "伤心欲绝",
+            "泪目",
+            "流泪",
+            "哭死",
+            "哭晕",
+            "想哭",
+            "泪崩",
+            "cry",
+            "crying",
+            "tears",
+            "sob",
+            "weep",
+        ],
+        "loving": [
+            "爱你",
+            "喜欢",
+            "爱",
+            "亲爱的",
+            "宝贝",
+            "么么哒",
+            "抱抱",
+            "想你",
+            "思念",
+            "最爱",
+            "亲亲",
+            "喜欢你",
+            "love",
+            "like",
+            "adore",
+            "darling",
+            "sweetie",
+            "honey",
+            "miss you",
+            "heart",
+        ],
+        "embarrassed": [
+            "尴尬",
+            "不好意思",
+            "害羞",
+            "脸红",
+            "难为情",
+            "社死",
+            "丢脸",
+            "出丑",
+            "embarrassed",
+            "awkward",
+            "shy",
+            "blush",
+        ],
+        "surprised": [
+            "惊讶",
+            "吃惊",
+            "天啊",
+            "哇塞",
+            "哇",
+            "居然",
+            "竟然",
+            "没想到",
+            "出乎意料",
+            "surprise",
+            "wow",
+            "omg",
+            "oh my god",
+            "amazing",
+            "unbelievable",
+        ],
+        "shocked": [
+            "震惊",
+            "吓到",
+            "惊呆了",
+            "不敢相信",
+            "震撼",
+            "吓死",
+            "恐怖",
+            "害怕",
+            "吓人",
+            "shocked",
+            "shocking",
+            "scared",
+            "frightened",
+            "terrified",
+            "horror",
+        ],
+        "thinking": [
+            "思考",
+            "考虑",
+            "想一下",
+            "琢磨",
+            "沉思",
+            "冥想",
+            "想",
+            "思考中",
+            "在想",
+            "think",
+            "thinking",
+            "consider",
+            "ponder",
+            "meditate",
+        ],
+        "winking": [
+            "调皮",
+            "眨眼",
+            "你懂的",
+            "坏笑",
+            "邪恶",
+            "奸笑",
+            "使眼色",
+            "wink",
+            "teasing",
+            "naughty",
+            "mischievous",
+        ],
+        "cool": [
+            "酷",
+            "帅",
+            "厉害",
+            "棒极了",
+            "真棒",
+            "牛逼",
+            "强",
+            "优秀",
+            "杰出",
+            "出色",
+            "完美",
+            "cool",
+            "awesome",
+            "amazing",
+            "great",
+            "impressive",
+            "perfect",
+        ],
+        "relaxed": [
+            "放松",
+            "舒服",
+            "惬意",
+            "悠闲",
+            "轻松",
+            "舒适",
+            "安逸",
+            "自在",
+            "relax",
+            "relaxed",
+            "comfortable",
+            "cozy",
+            "chill",
+            "peaceful",
+        ],
+        "delicious": [
+            "好吃",
+            "美味",
+            "香",
+            "馋",
+            "可口",
+            "香甜",
+            "大餐",
+            "大快朵颐",
+            "流口水",
+            "垂涎",
+            "delicious",
+            "yummy",
+            "tasty",
+            "yum",
+            "appetizing",
+            "mouthwatering",
+        ],
+        "kissy": [
+            "亲亲",
+            "么么",
+            "吻",
+            "mua",
+            "muah",
+            "亲一下",
+            "飞吻",
+            "kiss",
+            "xoxo",
+            "hug",
+            "muah",
+            "smooch",
+        ],
+        "confident": [
+            "自信",
+            "肯定",
+            "确定",
+            "毫无疑问",
+            "当然",
+            "必须的",
+            "毫无疑问",
+            "确信",
+            "坚信",
+            "confident",
+            "sure",
+            "certain",
+            "definitely",
+            "positive",
+        ],
+        "sleepy": [
+            "困",
+            "睡觉",
+            "晚安",
+            "想睡",
+            "好累",
+            "疲惫",
+            "疲倦",
+            "困了",
+            "想休息",
+            "睡意",
+            "sleep",
+            "sleepy",
+            "tired",
+            "exhausted",
+            "bedtime",
+            "good night",
+        ],
+        "silly": [
+            "傻",
+            "笨",
+            "呆",
+            "憨",
+            "蠢",
+            "二",
+            "憨憨",
+            "傻乎乎",
+            "呆萌",
+            "silly",
+            "stupid",
+            "dumb",
+            "foolish",
+            "goofy",
+            "ridiculous",
+        ],
+        "confused": [
+            "疑惑",
+            "不明白",
+            "不懂",
+            "困惑",
+            "疑问",
+            "为什么",
+            "怎么回事",
+            "啥意思",
+            "不清楚",
+            "confused",
+            "puzzled",
+            "doubt",
+            "question",
+            "what",
+            "why",
+            "how",
+        ],
     }
 
     # 特殊句型判断（中英文）
     # 赞美他人
-    if any(phrase in text for phrase in
+    if any(
-           ['你真', '你好', '您真', '你真棒', '你好厉害', '你太强了', '你真好', '你真聪明',
+        phrase in text
-            'you are', 'you\'re', 'you look', 'you seem', 'so smart', 'so kind']):
+        for phrase in [
-        return 'loving'
+            "你真",
+            "你好",
+            "您真",
+            "你真棒",
+            "你好厉害",
+            "你太强了",
+            "你真好",
+            "你真聪明",
+            "you are",
+            "you're",
+            "you look",
+            "you seem",
+            "so smart",
+            "so kind",
+        ]
+    ):
+        return "loving"
     # 自我赞美
-    if any(phrase in text for phrase in ['我真', '我最', '我太棒了', '我厉害', '我聪明', '我优秀',
+    if any(
-                                        'i am', 'i\'m', 'i feel', 'so good', 'so happy']):
+        phrase in text
-        return 'cool'
+        for phrase in [
+            "我真",
+            "我最",
+            "我太棒了",
+            "我厉害",
+            "我聪明",
+            "我优秀",
+            "i am",
+            "i'm",
+            "i feel",
+            "so good",
+            "so happy",
+        ]
+    ):
+        return "cool"
     # 晚安/睡觉相关
-    if any(phrase in text for phrase in ['睡觉', '晚安', '睡了', '好梦', '休息了', '去睡了',
+    if any(
-                                         'sleep', 'good night', 'bedtime', 'go to bed']):
+        phrase in text
-        return 'sleepy'
+        for phrase in [
+            "睡觉",
+            "晚安",
+            "睡了",
+            "好梦",
+            "休息了",
+            "去睡了",
+            "sleep",
+            "good night",
+            "bedtime",
+            "go to bed",
+        ]
+    ):
+        return "sleepy"
     # 疑问句
     if has_question and not has_exclamation:
-        return 'thinking'
+        return "thinking"
     # 强烈情感（感叹号）
     if has_exclamation and not has_question:
         # 检查是否是积极内容
-        positive_words = emotion_keywords['happy'] + emotion_keywords['laughing'] + emotion_keywords['cool']
+        positive_words = (
+            emotion_keywords["happy"]
+            + emotion_keywords["laughing"]
+            + emotion_keywords["cool"]
+        )
         if any(word in text for word in positive_words):
-            return 'laughing'
+            return "laughing"
         # 检查是否是消极内容
-        negative_words = emotion_keywords['angry'] + emotion_keywords['sad'] + emotion_keywords['crying']
+        negative_words = (
+            emotion_keywords["angry"]
+            + emotion_keywords["sad"]
+            + emotion_keywords["crying"]
+        )
         if any(word in text for word in negative_words):
-            return 'angry'
+            return "angry"
-        return 'surprised'
+        return "surprised"
     # 省略号（表示犹豫或思考）
     if has_ellipsis:
-        return 'thinking'
+        return "thinking"
 
     # 关键词匹配（带权重）
     emotion_scores = {emotion: 0 for emotion in emoji_map.keys()}
@@ -466,18 +832,33 @@ def analyze_emotion(text):
     # 根据分数选择最可能的情感
     max_score = max(emotion_scores.values())
     if max_score == 0:
-        return 'happy'  # 默认
+        return "happy"  # 默认
 
     # 可能有多个情感同分，根据上下文选择最合适的
     top_emotions = [e for e, s in emotion_scores.items() if s == max_score]
 
     # 如果多个情感同分，使用以下优先级
     priority_order = [
-        'laughing', 'crying', 'angry', 'surprised', 'shocked',  # 强烈情感优先
+        "laughing",
-        'loving', 'happy', 'funny', 'cool',  # 积极情感
+        "crying",
-        'sad', 'embarrassed', 'confused',  # 消极情感
+        "angry",
-        'thinking', 'winking', 'relaxed',  # 中性情感
+        "surprised",
-        'delicious', 'kissy', 'confident', 'sleepy', 'silly'  # 特殊场景
+        "shocked",  # 强烈情感优先
+        "loving",
+        "happy",
+        "funny",
+        "cool",  # 积极情感
+        "sad",
+        "embarrassed",
+        "confused",  # 消极情感
+        "thinking",
+        "winking",
+        "relaxed",  # 中性情感
+        "delicious",
+        "kissy",
+        "confident",
+        "sleepy",
+        "silly",  # 特殊场景
     ]
 
     for emotion in priority_order:
@@ -485,3 +866,50 @@ def analyze_emotion(text):
             return emotion
 
     return top_emotions[0]  # 如果都不在优先级列表里，返回第一个
+
+
+def audio_to_opus_data(audio_file_path):
+    """音频文件转换为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)
+
+    # 音频时长(秒)
+    duration = len(audio) / 1000.0
+
+    # 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
+
+    opus_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))
+
+        # 转换为numpy数组处理
+        np_frame = np.frombuffer(chunk, dtype=np.int16)
+
+        # 编码Opus数据
+        opus_data = encoder.encode(np_frame.tobytes(), frame_size)
+        opus_datas.append(opus_data)
+
+    return opus_datas, duration