From b6684fe7a38298776b88955a7d5b86ba39b3bc31 Mon Sep 17 00:00:00 2001 From: zwssunny Date: Mon, 27 Mar 2023 14:11:05 +0800 Subject: [PATCH 1/9] =?UTF-8?q?=E5=A2=9E=E5=8A=A0=E5=A3=B0=E9=9F=B3?= =?UTF-8?q?=E8=BD=AC=E6=8D=A2=E5=87=BD=E6=95=B0?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- requirements.txt | 13 +++++++++ voice/audio_convert.py | 60 ++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 73 insertions(+) create mode 100644 voice/audio_convert.py diff --git a/requirements.txt b/requirements.txt index 98dd5af..42aa17c 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,3 +1,16 @@ itchat-uos==1.5.0.dev0 openai wechaty +tiktoken +whisper +baidu-aip +chardet +ffmpy +pydub +pilk +pysilk +pysilk-mod +wave +SpeechRecognition +pyttsx3 +gTTS diff --git a/voice/audio_convert.py b/voice/audio_convert.py new file mode 100644 index 0000000..73d18c8 --- /dev/null +++ b/voice/audio_convert.py @@ -0,0 +1,60 @@ +import wave +import pysilk +from pydub import AudioSegment + + +def get_pcm_from_wav(wav_path): + """ + 从 wav 文件中读取 pcm + + :param wav_path: wav 文件路径 + :returns: pcm 数据 + """ + wav = wave.open(wav_path, "rb") + return wav.readframes(wav.getnframes()) + + +def mp3_to_wav(mp3_path, wav_path): + """ + 把mp3格式转成pcm文件 + """ + audio = AudioSegment.from_mp3(mp3_path) + audio.export(wav_path, format="wav") + + +def pcm_to_silk(pcm_path, silk_path): + """ + wav 文件转成 silk + return 声音长度，毫秒 + """ + audio = AudioSegment.from_wav(pcm_path) + wav_data = audio.raw_data + silk_data = pysilk.encode( + wav_data, data_rate=audio.frame_rate, sample_rate=audio.frame_rate) + with open(silk_path, "wb") as f: + f.write(silk_data) + return audio.duration_seconds * 1000 + + +def mp3_to_sil(mp3_path, silk_path): + """ + mp3 文件转成 silk + return 声音长度，毫秒 + """ + audio = AudioSegment.from_mp3(mp3_path) + wav_data = audio.raw_data + silk_data = pysilk.encode( + wav_data, data_rate=audio.frame_rate, sample_rate=audio.frame_rate) + # Save the silk file + with open(silk_path, "wb") as f: + f.write(silk_data) + return audio.duration_seconds * 1000 + + +def sil_to_wav(silk_path, wav_path, rate: int = 24000): + """ + silk 文件转 wav + """ + wav_data = pysilk.decode_file(silk_path, to_wav=True, sample_rate=rate) + with open(wav_path, "wb") as f: + f.write(wav_data) From c2ea6214a9ac1800250fdb071a472ea0d2e864c0 Mon Sep 17 00:00:00 2001 From: zwssunny Date: Mon, 27 Mar 2023 14:40:19 +0800 Subject: [PATCH 2/9] =?UTF-8?q?=E5=A2=9E=E5=8A=A0=E7=99=BE=E5=BA=A6?= =?UTF-8?q?=E8=AF=AD=E9=9F=B3=E8=AF=86=E5=88=AB?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- config.py | 111 ++++++++++++++++++++----------------- voice/baidu/baidu_voice.py | 41 +++++++++++++- 2 files changed, 97 insertions(+), 55 deletions(-) diff --git a/config.py b/config.py index cf67745..5732969 100644 --- a/config.py +++ b/config.py @@ -5,71 +5,76 @@ import os from common.log import logger # 将所有可用的配置项写在字典里, 请使用小写字母 -available_setting ={ - #openai api配置 - "open_ai_api_key": "", # openai api key - "open_ai_api_base": "https://api.openai.com/v1", # openai apibase，当use_azure_chatgpt为true时，需要设置对应的api base - "proxy": "", # openai使用的代理 - "model": "gpt-3.5-turbo", # chatgpt模型， 当use_azure_chatgpt为true时，其名称为Azure上model deployment名称 - "use_azure_chatgpt": False, # 是否使用azure的chatgpt - - #Bot触发配置 - "single_chat_prefix": ["bot", "@bot"], # 私聊时文本需要包含该前缀才能触发机器人回复 - "single_chat_reply_prefix": "[bot] ", # 私聊时自动回复的前缀，用于区分真人 - "group_chat_prefix": ["@bot"], # 群聊时包含该前缀则会触发机器人回复 - "group_chat_reply_prefix": "", # 群聊时自动回复的前缀 - "group_chat_keyword": [], # 群聊时包含该关键词则会触发机器人回复 - "group_at_off": False, # 是否关闭群聊时@bot的触发 - "group_name_white_list": ["ChatGPT测试群", "ChatGPT测试群2"], # 开启自动回复的群名称列表 - "group_name_keyword_white_list": [], # 开启自动回复的群名称关键词列表 - "group_chat_in_one_session": ["ChatGPT测试群"], # 支持会话上下文共享的群名称 - "image_create_prefix": ["画", "看", "找"], # 开启图片回复的前缀 - - #chatgpt会话参数 - "expires_in_seconds": 3600, # 无操作会话的过期时间 - "character_desc": "你是ChatGPT, 一个由OpenAI训练的大型语言模型, 你旨在回答并解决人们的任何问题，并且可以使用多种语言与人交流。", # 人格描述 - "conversation_max_tokens": 1000, # 支持上下文记忆的最多字符数 - - #chatgpt限流配置 - "rate_limit_chatgpt": 20, # chatgpt的调用频率限制 - "rate_limit_dalle": 50, # openai dalle的调用频率限制 - - - #chatgpt api参数 参考https://platform.openai.com/docs/api-reference/chat/create +available_setting = { + # openai api配置 + "open_ai_api_key": "", # openai api key + # openai apibase，当use_azure_chatgpt为true时，需要设置对应的api base + "open_ai_api_base": "https://api.openai.com/v1", + "proxy": "", # openai使用的代理 + # chatgpt模型， 当use_azure_chatgpt为true时，其名称为Azure上model deployment名称 + "model": "gpt-3.5-turbo", + "use_azure_chatgpt": False, # 是否使用azure的chatgpt + + # Bot触发配置 + "single_chat_prefix": ["bot", "@bot"], # 私聊时文本需要包含该前缀才能触发机器人回复 + "single_chat_reply_prefix": "[bot] ", # 私聊时自动回复的前缀，用于区分真人 + "group_chat_prefix": ["@bot"], # 群聊时包含该前缀则会触发机器人回复 + "group_chat_reply_prefix": "", # 群聊时自动回复的前缀 + "group_chat_keyword": [], # 群聊时包含该关键词则会触发机器人回复 + "group_at_off": False, # 是否关闭群聊时@bot的触发 + "group_name_white_list": ["ChatGPT测试群", "ChatGPT测试群2"], # 开启自动回复的群名称列表 + "group_name_keyword_white_list": [], # 开启自动回复的群名称关键词列表 + "group_chat_in_one_session": ["ChatGPT测试群"], # 支持会话上下文共享的群名称 + "image_create_prefix": ["画", "看", "找"], # 开启图片回复的前缀 + + # chatgpt会话参数 + "expires_in_seconds": 3600, # 无操作会话的过期时间 + "character_desc": "你是ChatGPT, 一个由OpenAI训练的大型语言模型, 你旨在回答并解决人们的任何问题，并且可以使用多种语言与人交流。", # 人格描述 + "conversation_max_tokens": 1000, # 支持上下文记忆的最多字符数 + + # chatgpt限流配置 + "rate_limit_chatgpt": 20, # chatgpt的调用频率限制 + "rate_limit_dalle": 50, # openai dalle的调用频率限制 + + + # chatgpt api参数 参考https://platform.openai.com/docs/api-reference/chat/create "temperature": 0.9, "top_p": 1, "frequency_penalty": 0, "presence_penalty": 0, - #语音设置 - "speech_recognition": False, # 是否开启语音识别 - "group_speech_recognition": False, # 是否开启群组语音识别 - "voice_reply_voice": False, # 是否使用语音回复语音，需要设置对应语音合成引擎的api key - "voice_to_text": "openai", # 语音识别引擎，支持openai和google - "text_to_voice": "baidu", # 语音合成引擎，支持baidu和google + # 语音设置 + "speech_recognition": False, # 是否开启语音识别 + "group_speech_recognition": False, # 是否开启群组语音识别 + "voice_reply_voice": False, # 是否使用语音回复语音，需要设置对应语音合成引擎的api key + "voice_to_text": "openai", # 语音识别引擎，支持openai和google + "text_to_voice": "baidu", # 语音合成引擎，支持baidu和google # baidu api的配置， 使用百度语音识别和语音合成时需要 - 'baidu_app_id': "", - 'baidu_api_key': "", - 'baidu_secret_key': "", + "baidu_app_id": "", + "baidu_api_key": "", + "baidu_secret_key": "", + # 1536普通话(支持简单的英文识别) 1737英语 1637粤语 1837四川话 1936普通话远场 + "baidu_dev_pid": "1536", - #服务时间限制，目前支持itchat - "chat_time_module": False, # 是否开启服务时间限制 - "chat_start_time": "00:00", # 服务开始时间 - "chat_stop_time": "24:00", # 服务结束时间 + # 服务时间限制，目前支持itchat + "chat_time_module": False, # 是否开启服务时间限制 + "chat_start_time": "00:00", # 服务开始时间 + "chat_stop_time": "24:00", # 服务结束时间 # itchat的配置 - "hot_reload": False, # 是否开启热重载 + "hot_reload": False, # 是否开启热重载 # wechaty的配置 - "wechaty_puppet_service_token": "", # wechaty的token + "wechaty_puppet_service_token": "", # wechaty的token # chatgpt指令自定义触发词 - "clear_memory_commands": ['#清除记忆'], # 重置会话指令 + "clear_memory_commands": ['#清除记忆'], # 重置会话指令 } + class Config(dict): def __getitem__(self, key): if key not in available_setting: @@ -82,15 +87,17 @@ class Config(dict): return super().__setitem__(key, value) def get(self, key, default=None): - try : + try: return self[key] except KeyError as e: return default except Exception as e: raise e - + + config = Config() + def load_config(): global config config_path = "./config.json" @@ -109,7 +116,8 @@ def load_config(): for name, value in os.environ.items(): name = name.lower() if name in available_setting: - logger.info("[INIT] override config by environ args: {}={}".format(name, value)) + logger.info( + "[INIT] override config by environ args: {}={}".format(name, value)) try: config[name] = eval(value) except: @@ -118,9 +126,8 @@ def load_config(): logger.info("[INIT] load config: {}".format(config)) - def get_root(): - return os.path.dirname(os.path.abspath( __file__ )) + return os.path.dirname(os.path.abspath(__file__)) def read_file(path): diff --git a/voice/baidu/baidu_voice.py b/voice/baidu/baidu_voice.py index 531d8ce..73375bd 100644 --- a/voice/baidu/baidu_voice.py +++ b/voice/baidu/baidu_voice.py @@ -8,19 +8,53 @@ from bridge.reply import Reply, ReplyType from common.log import logger from common.tmp_dir import TmpDir from voice.voice import Voice +from voice.audio_convert import get_pcm_from_wav from config import conf +""" + 百度的语音识别API. + dev_pid: + - 1936: 普通话远场 + - 1536：普通话(支持简单的英文识别) + - 1537：普通话(纯中文识别) + - 1737：英语 + - 1637：粤语 + - 1837：四川话 + 要使用本模块, 首先到 yuyin.baidu.com 注册一个开发者账号, + 之后创建一个新应用, 然后在应用管理的"查看key"中获得 API Key 和 Secret Key + 填入 config.json 中. + baidu_app_id: '' + baidu_api_key: '' + baidu_secret_key: '' + baidu_dev_pid: '1536' +""" + class BaiduVoice(Voice): APP_ID = conf().get('baidu_app_id') API_KEY = conf().get('baidu_api_key') SECRET_KEY = conf().get('baidu_secret_key') + DEV_ID = conf().get('baidu_dev_pid') client = AipSpeech(APP_ID, API_KEY, SECRET_KEY) - + def __init__(self): pass def voiceToText(self, voice_file): - pass + # 识别本地文件 + logger.debug('[Baidu] voice file name={}'.format(voice_file)) + pcm = get_pcm_from_wav(voice_file) + res = self.client.asr(pcm, "pcm", 16000, {"dev_pid": self.DEV_ID}) + if res["err_no"] == 0: + logger.info("百度语音识别到了：{}".format(res["result"])) + text = "".join(res["result"]) + reply = Reply(ReplyType.TEXT, text) + else: + logger.info("百度语音识别出错了: {}".format(res["err_msg"])) + if res["err_msg"] == "request pv too much": + logger.info(" 出现这个原因很可能是你的百度语音服务调用量超出限制，或未开通付费") + reply = Reply(ReplyType.ERROR, + "百度语音识别出错了；{0}".format(res["err_msg"])) + return reply def textToVoice(self, text): result = self.client.synthesis(text, 'zh', 1, { @@ -30,7 +64,8 @@ class BaiduVoice(Voice): fileName = TmpDir().path() + '语音回复_' + str(int(time.time())) + '.mp3' with open(fileName, 'wb') as f: f.write(result) - logger.info('[Baidu] textToVoice text={} voice file name={}'.format(text, fileName)) + logger.info( + '[Baidu] textToVoice text={} voice file name={}'.format(text, fileName)) reply = Reply(ReplyType.VOICE, fileName) else: logger.error('[Baidu] textToVoice error={}'.format(result)) From 61865bc40834327dc09d3ccaef9562087ba996ab Mon Sep 17 00:00:00 2001 From: zwssunny Date: Mon, 27 Mar 2023 14:54:00 +0800 Subject: [PATCH 3/9] =?UTF-8?q?=E4=BF=AE=E6=94=B9google=5Fvoice=E4=B8=BAgo?= =?UTF-8?q?ogle=E5=90=88=E6=88=90=EF=BC=8C=E8=A7=A3=E5=86=B3=E7=B3=BB?= =?UTF-8?q?=E7=BB=9F=E5=85=BC=E5=AE=B9=E6=80=A7?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- voice/google/google_voice.py | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) diff --git a/voice/google/google_voice.py b/voice/google/google_voice.py index 74431db..2cc9851 100644 --- a/voice/google/google_voice.py +++ b/voice/google/google_voice.py @@ -9,9 +9,11 @@ import time from bridge.reply import Reply, ReplyType import speech_recognition import pyttsx3 +from gtts import gTTS from common.log import logger from common.tmp_dir import TmpDir from voice.voice import Voice +from voice.audio_convert import mp3_to_wav class GoogleVoice(Voice): @@ -29,8 +31,9 @@ class GoogleVoice(Voice): def voiceToText(self, voice_file): new_file = voice_file.replace('.mp3', '.wav') - subprocess.call('ffmpeg -i ' + voice_file + - ' -acodec pcm_s16le -ac 1 -ar 16000 ' + new_file, shell=True) + # subprocess.call('ffmpeg -i ' + voice_file + + # ' -acodec pcm_s16le -ac 1 -ar 16000 ' + new_file, shell=True) + mp3_to_wav(voice_file, new_file) with speech_recognition.AudioFile(new_file) as source: audio = self.recognizer.record(source) try: @@ -46,12 +49,14 @@ class GoogleVoice(Voice): return reply def textToVoice(self, text): try: - textFile = TmpDir().path() + '语音回复_' + str(int(time.time())) + '.mp3' - self.engine.save_to_file(text, textFile) - self.engine.runAndWait() + mp3File = TmpDir().path() + '语音回复_' + str(int(time.time())) + '.mp3' + # self.engine.save_to_file(text, textFile) + # self.engine.runAndWait() + tts = gTTS(text=text, lang='zh') + tts.save(mp3File) logger.info( - '[Google] textToVoice text={} voice file name={}'.format(text, textFile)) - reply = Reply(ReplyType.VOICE, textFile) + '[Google] textToVoice text={} voice file name={}'.format(text, mp3File)) + reply = Reply(ReplyType.VOICE, mp3File) except Exception as e: reply = Reply(ReplyType.ERROR, str(e)) finally: From b3cb81aa52acf496319b398e31d8c70035a34c8f Mon Sep 17 00:00:00 2001 From: zwssunny Date: Mon, 27 Mar 2023 16:13:58 +0800 Subject: [PATCH 4/9] =?UTF-8?q?wx=E9=A2=91=E9=81=93=E5=A2=9E=E5=8A=A0?= =?UTF-8?q?=E7=BE=A4=E8=AF=AD=E9=9F=B3=E8=81=8A=E5=A4=A9=E5=8A=9F=E8=83=BD?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- channel/wechat/wechat_channel.py | 133 ++++++++++++++++++++++--------- 1 file changed, 96 insertions(+), 37 deletions(-) diff --git a/channel/wechat/wechat_channel.py b/channel/wechat/wechat_channel.py index fa303d2..5aad491 100644 --- a/channel/wechat/wechat_channel.py +++ b/channel/wechat/wechat_channel.py @@ -23,10 +23,14 @@ import time thread_pool = ThreadPoolExecutor(max_workers=8) + + def thread_pool_callback(worker): worker_exception = worker.exception() if worker_exception: - logger.exception("Worker return exception: {}".format(worker_exception)) + logger.exception( + "Worker return exception: {}".format(worker_exception)) + @itchat.msg_register(TEXT) def handler_single_msg(msg): @@ -46,20 +50,27 @@ def handler_single_voice(msg): return None +@itchat.msg_register(VOICE, isGroupChat=True) +def handler_group_voice(msg): + WechatChannel().handle_group_voice(msg) + return None + + class WechatChannel(Channel): def __init__(self): pass def startup(self): - itchat.instance.receivingRetryCount = 600 # 修改断线超时时间 + itchat.instance.receivingRetryCount = 600 # 修改断线超时时间 # login by scan QRCode hotReload = conf().get('hot_reload', False) try: itchat.auto_login(enableCmdQR=2, hotReload=hotReload) except Exception as e: if hotReload: - logger.error("Hot reload failed, try to login without hot reload") + logger.error( + "Hot reload failed, try to login without hot reload") itchat.logout() os.remove("itchat.pkl") itchat.auto_login(enableCmdQR=2, hotReload=hotReload) @@ -85,21 +96,23 @@ class WechatChannel(Channel): from_user_id = msg['FromUserName'] other_user_id = msg['User']['UserName'] if from_user_id == other_user_id: - context = Context(ContextType.VOICE,msg['FileName']) - context.kwargs = {'isgroup': False, 'msg': msg, 'receiver': other_user_id, 'session_id': other_user_id} - thread_pool.submit(self.handle, context).add_done_callback(thread_pool_callback) - + context = Context(ContextType.VOICE, msg['FileName']) + context.kwargs = {'isgroup': False, 'msg': msg, + 'receiver': other_user_id, 'session_id': other_user_id} + thread_pool.submit(self.handle, context).add_done_callback( + thread_pool_callback) @time_checker def handle_text(self, msg): - logger.debug("[WX]receive text msg: " + json.dumps(msg, ensure_ascii=False)) + logger.debug("[WX]receive text msg: " + + json.dumps(msg, ensure_ascii=False)) content = msg['Text'] from_user_id = msg['FromUserName'] to_user_id = msg['ToUserName'] # 接收人id other_user_id = msg['User']['UserName'] # 对手方id create_time = msg['CreateTime'] # 消息时间 match_prefix = check_prefix(content, conf().get('single_chat_prefix')) - if conf().get('hot_reload') == True and int(create_time) < int(time.time()) - 60: #跳过1分钟前的历史消息 + if conf().get('hot_reload') == True and int(create_time) < int(time.time()) - 60: # 跳过1分钟前的历史消息 logger.debug("[WX]history message skipped") return if "」\n- - - - - - - - - - - - - - -" in content: @@ -110,9 +123,11 @@ class WechatChannel(Channel): elif match_prefix is None: return context = Context() - context.kwargs = {'isgroup': False, 'msg': msg, 'receiver': other_user_id, 'session_id': other_user_id} + context.kwargs = {'isgroup': False, 'msg': msg, + 'receiver': other_user_id, 'session_id': other_user_id} - img_match_prefix = check_prefix(content, conf().get('image_create_prefix')) + img_match_prefix = check_prefix( + content, conf().get('image_create_prefix')) if img_match_prefix: content = content.replace(img_match_prefix, '', 1).strip() context.type = ContextType.IMAGE_CREATE @@ -120,15 +135,17 @@ class WechatChannel(Channel): context.type = ContextType.TEXT context.content = content - thread_pool.submit(self.handle, context).add_done_callback(thread_pool_callback) + thread_pool.submit(self.handle, context).add_done_callback( + thread_pool_callback) @time_checker def handle_group(self, msg): - logger.debug("[WX]receive group msg: " + json.dumps(msg, ensure_ascii=False)) + logger.debug("[WX]receive group msg: " + + json.dumps(msg, ensure_ascii=False)) group_name = msg['User'].get('NickName', None) group_id = msg['User'].get('UserName', None) create_time = msg['CreateTime'] # 消息时间 - if conf().get('hot_reload') == True and int(create_time) < int(time.time()) - 60: #跳过1分钟前的历史消息 + if conf().get('hot_reload') == True and int(create_time) < int(time.time()) - 60: # 跳过1分钟前的历史消息 logger.debug("[WX]history group message skipped") return if not group_name: @@ -146,12 +163,14 @@ class WechatChannel(Channel): return "" config = conf() match_prefix = (msg['IsAt'] and not config.get("group_at_off", False)) or check_prefix(origin_content, config.get('group_chat_prefix')) \ - or check_contain(origin_content, config.get('group_chat_keyword')) + or check_contain(origin_content, config.get('group_chat_keyword')) if ('ALL_GROUP' in config.get('group_name_white_list') or group_name in config.get('group_name_white_list') or check_contain(group_name, config.get('group_name_keyword_white_list'))) and match_prefix: context = Context() - context.kwargs = { 'isgroup': True, 'msg': msg, 'receiver': group_id} - - img_match_prefix = check_prefix(content, conf().get('image_create_prefix')) + context.kwargs = {'isgroup': True, + 'msg': msg, 'receiver': group_id} + + img_match_prefix = check_prefix( + content, conf().get('image_create_prefix')) if img_match_prefix: content = content.replace(img_match_prefix, '', 1).strip() context.type = ContextType.IMAGE_CREATE @@ -167,10 +186,24 @@ class WechatChannel(Channel): else: context['session_id'] = msg['ActualUserName'] - thread_pool.submit(self.handle, context).add_done_callback(thread_pool_callback) + thread_pool.submit(self.handle, context).add_done_callback( + thread_pool_callback) + + def handle_group_voice(self, msg): + if conf().get('speech_recognition') != True: + return + logger.debug("[WX]receive group voice msg: " + msg['FileName']) + group_name = msg['User'].get('NickName', None) + group_id = msg['User'].get('UserName', None) + from_user_id = msg['ActualUserName'] + context = Context(ContextType.VOICE, msg['FileName']) + context.kwargs = {'isgroup': True, 'msg': msg, + 'receiver': group_id, 'session_id': from_user_id} + thread_pool.submit(self.handle, context).add_done_callback( + thread_pool_callback) # 统一的发送函数，每个Channel自行实现，根据reply的type字段发送不同类型的消息 - def send(self, reply : Reply, receiver): + def send(self, reply: Reply, receiver): if reply.type == ReplyType.TEXT: itchat.send(reply.content, toUserName=receiver) logger.info('[WX] sendMsg={}, receiver={}'.format(reply, receiver)) @@ -179,8 +212,9 @@ class WechatChannel(Channel): logger.info('[WX] sendMsg={}, receiver={}'.format(reply, receiver)) elif reply.type == ReplyType.VOICE: itchat.send_file(reply.content, toUserName=receiver) - logger.info('[WX] sendFile={}, receiver={}'.format(reply.content, receiver)) - elif reply.type == ReplyType.IMAGE_URL: # 从网络下载图片 + logger.info('[WX] sendFile={}, receiver={}'.format( + reply.content, receiver)) + elif reply.type == ReplyType.IMAGE_URL: # 从网络下载图片 img_url = reply.content pic_res = requests.get(img_url, stream=True) image_storage = io.BytesIO() @@ -188,8 +222,9 @@ class WechatChannel(Channel): image_storage.write(block) image_storage.seek(0) itchat.send_image(image_storage, toUserName=receiver) - logger.info('[WX] sendImage url={}, receiver={}'.format(img_url,receiver)) - elif reply.type == ReplyType.IMAGE: # 从文件读取图片 + logger.info('[WX] sendImage url={}, receiver={}'.format( + img_url, receiver)) + elif reply.type == ReplyType.IMAGE: # 从文件读取图片 image_storage = reply.content image_storage.seek(0) itchat.send_image(image_storage, toUserName=receiver) @@ -200,12 +235,14 @@ class WechatChannel(Channel): reply = Reply() logger.debug('[WX] ready to handle context: {}'.format(context)) - + # reply的构建步骤 - e_context = PluginManager().emit_event(EventContext(Event.ON_HANDLE_CONTEXT, {'channel' : self, 'context': context, 'reply': reply})) + e_context = PluginManager().emit_event(EventContext(Event.ON_HANDLE_CONTEXT, { + 'channel': self, 'context': context, 'reply': reply})) reply = e_context['reply'] if not e_context.is_pass(): - logger.debug('[WX] ready to handle context: type={}, content={}'.format(context.type, context.content)) + logger.debug('[WX] ready to handle context: type={}, content={}'.format( + context.type, context.content)) if context.type == ContextType.TEXT or context.type == ContextType.IMAGE_CREATE: reply = super().build_reply_content(context.content, context) elif context.type == ContextType.VOICE: @@ -214,8 +251,24 @@ class WechatChannel(Channel): msg.download(file_name) reply = super().build_voice_to_text(file_name) if reply.type != ReplyType.ERROR and reply.type != ReplyType.INFO: - context.content = reply.content # 语音转文字后，将文字内容作为新的context + context.content = reply.content # 语音转文字后，将文字内容作为新的context context.type = ContextType.TEXT + if (context["isgroup"] == True): + # 校验关键字 + match_prefix = self.check_prefix(context.content, conf().get('group_chat_prefix')) \ + or self.check_contain(context.content, conf().get('group_chat_keyword')) + # Wechaty判断is_at为True，返回的内容是过滤掉@之后的内容；而is_at为False，则会返回完整的内容 + if match_prefix is not None: + # 故判断如果匹配到自定义前缀，则返回过滤掉前缀+空格后的内容，用于实现类似自定义+前缀触发生成AI图片的功能 + prefixes = conf().get('group_chat_prefix') + for prefix in prefixes: + if context.content.startswith(prefix): + context.content = context.content.replace(prefix, '', 1).strip() + break + else: + logger.info("[WX]receive voice check prefix: " + 'False') + return + reply = super().build_reply_content(context.content, context) if reply.type == ReplyType.TEXT: if conf().get('voice_reply_voice'): @@ -225,16 +278,19 @@ class WechatChannel(Channel): return logger.debug('[WX] ready to decorate reply: {}'.format(reply)) - + # reply的包装步骤 if reply and reply.type: - e_context = PluginManager().emit_event(EventContext(Event.ON_DECORATE_REPLY, {'channel' : self, 'context': context, 'reply': reply})) - reply=e_context['reply'] + e_context = PluginManager().emit_event(EventContext(Event.ON_DECORATE_REPLY, { + 'channel': self, 'context': context, 'reply': reply})) + reply = e_context['reply'] if not e_context.is_pass() and reply and reply.type: if reply.type == ReplyType.TEXT: reply_text = reply.content if context['isgroup']: - reply_text = '@' + context['msg']['ActualNickName'] + ' ' + reply_text.strip() + reply_text = '@' + \ + context['msg']['ActualNickName'] + \ + ' ' + reply_text.strip() reply_text = conf().get("group_chat_reply_prefix", "")+reply_text else: reply_text = conf().get("single_chat_reply_prefix", "")+reply_text @@ -244,15 +300,18 @@ class WechatChannel(Channel): elif reply.type == ReplyType.IMAGE_URL or reply.type == ReplyType.VOICE or reply.type == ReplyType.IMAGE: pass else: - logger.error('[WX] unknown reply type: {}'.format(reply.type)) + logger.error( + '[WX] unknown reply type: {}'.format(reply.type)) return - # reply的发送步骤 + # reply的发送步骤 if reply and reply.type: - e_context = PluginManager().emit_event(EventContext(Event.ON_SEND_REPLY, {'channel' : self, 'context': context, 'reply': reply})) - reply=e_context['reply'] + e_context = PluginManager().emit_event(EventContext(Event.ON_SEND_REPLY, { + 'channel': self, 'context': context, 'reply': reply})) + reply = e_context['reply'] if not e_context.is_pass() and reply and reply.type: - logger.debug('[WX] ready to send reply: {} to {}'.format(reply, context['receiver'])) + logger.debug('[WX] ready to send reply: {} to {}'.format( + reply, context['receiver'])) self.send(reply, context['receiver']) From 24de670c2c20e4552b6909c1fc8dc399e2af530f Mon Sep 17 00:00:00 2001 From: zwssunny Date: Mon, 27 Mar 2023 16:53:59 +0800 Subject: [PATCH 5/9] =?UTF-8?q?=E8=A7=A3=E5=86=B3=E8=AF=AD=E9=9F=B3?= =?UTF-8?q?=E7=9A=84=E8=AF=86=E5=88=AB=E5=92=8C=E8=BD=AC=E6=8D=A2=E5=85=BC?= =?UTF-8?q?=E5=AE=B9=E6=80=A7?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- channel/wechat/wechat_channel.py | 28 +++++++---- channel/wechat/wechaty_channel.py | 82 ++++++------------------------- voice/google/google_voice.py | 10 ++-- 3 files changed, 37 insertions(+), 83 deletions(-) diff --git a/channel/wechat/wechat_channel.py b/channel/wechat/wechat_channel.py index 5aad491..3d2c26a 100644 --- a/channel/wechat/wechat_channel.py +++ b/channel/wechat/wechat_channel.py @@ -5,6 +5,9 @@ wechat channel """ import os +import requests +import io +import time from lib import itchat import json from lib.itchat.content import * @@ -17,9 +20,7 @@ from common.tmp_dir import TmpDir from config import conf from common.time_check import time_checker from plugins import * -import requests -import io -import time +from voice.audio_convert import mp3_to_wav thread_pool = ThreadPoolExecutor(max_workers=8) @@ -28,8 +29,7 @@ thread_pool = ThreadPoolExecutor(max_workers=8) def thread_pool_callback(worker): worker_exception = worker.exception() if worker_exception: - logger.exception( - "Worker return exception: {}".format(worker_exception)) + logger.exception("Worker return exception: {}".format(worker_exception)) @itchat.msg_register(TEXT) @@ -247,9 +247,16 @@ class WechatChannel(Channel): reply = super().build_reply_content(context.content, context) elif context.type == ContextType.VOICE: msg = context['msg'] - file_name = TmpDir().path() + context.content - msg.download(file_name) - reply = super().build_voice_to_text(file_name) + mp3_path = TmpDir().path() + context.content + msg.download(mp3_path) + # mp3转wav + wav_path = os.path.splitext(mp3_path)[0] + '.wav' + mp3_to_wav(mp3_path=mp3_path, wav_path=wav_path) + # 语音识别 + reply = super().build_voice_to_text(wav_path) + # 删除临时文件 + os.remove(wav_path) + os.remove(mp3_path) if reply.type != ReplyType.ERROR and reply.type != ReplyType.INFO: context.content = reply.content # 语音转文字后，将文字内容作为新的context context.type = ContextType.TEXT @@ -263,12 +270,13 @@ class WechatChannel(Channel): prefixes = conf().get('group_chat_prefix') for prefix in prefixes: if context.content.startswith(prefix): - context.content = context.content.replace(prefix, '', 1).strip() + context.content = context.content.replace( + prefix, '', 1).strip() break else: logger.info("[WX]receive voice check prefix: " + 'False') return - + reply = super().build_reply_content(context.content, context) if reply.type == ReplyType.TEXT: if conf().get('voice_reply_voice'): diff --git a/channel/wechat/wechaty_channel.py b/channel/wechat/wechaty_channel.py index 1caf5b4..cc7788a 100644 --- a/channel/wechat/wechaty_channel.py +++ b/channel/wechat/wechaty_channel.py @@ -4,25 +4,19 @@ wechaty channel Python Wechaty - https://github.com/wechaty/python-wechaty """ -import io import os -import json import time import asyncio -import requests -import pysilk -import wave -from pydub import AudioSegment from typing import Optional, Union from bridge.context import Context, ContextType from wechaty_puppet import MessageType, FileBox, ScanStatus # type: ignore from wechaty import Wechaty, Contact -from wechaty.user import Message, Room, MiniProgram, UrlLink +from wechaty.user import Message, MiniProgram, UrlLink from channel.channel import Channel from common.log import logger from common.tmp_dir import TmpDir from config import conf - +from voice.audio_convert import sil_to_wav, mp3_to_sil class WechatyChannel(Channel): @@ -50,8 +44,8 @@ class WechatyChannel(Channel): async def on_scan(self, status: ScanStatus, qr_code: Optional[str] = None, data: Optional[str] = None): - contact = self.Contact.load(self.contact_id) - logger.info('[WX] scan user={}, scan status={}, scan qr_code={}'.format(contact, status.name, qr_code)) + # contact = self.Contact.load(self.contact_id) + # logger.info('[WX] scan user={}, scan status={}, scan qr_code={}'.format(contact, status.name, qr_code)) # print(f'user <{contact}> scan status: {status.name} , 'f'qr_code: {qr_code}') async def on_message(self, msg: Message): @@ -67,7 +61,7 @@ class WechatyChannel(Channel): content = msg.text() mention_content = await msg.mention_text() # 返回过滤掉@name后的消息 match_prefix = self.check_prefix(content, conf().get('single_chat_prefix')) - conversation: Union[Room, Contact] = from_contact if room is None else room + # conversation: Union[Room, Contact] = from_contact if room is None else room if room is None and msg.type() == MessageType.MESSAGE_TYPE_TEXT: if not msg.is_self() and match_prefix is not None: @@ -102,21 +96,8 @@ class WechatyChannel(Channel): await voice_file.to_file(silk_file) logger.info("[WX]receive voice file: " + silk_file) # 将文件转成wav格式音频 - wav_file = silk_file.replace(".slk", ".wav") - with open(silk_file, 'rb') as f: - silk_data = f.read() - pcm_data = pysilk.decode(silk_data) - - with wave.open(wav_file, 'wb') as wav_data: - wav_data.setnchannels(1) - wav_data.setsampwidth(2) - wav_data.setframerate(24000) - wav_data.writeframes(pcm_data) - if os.path.exists(wav_file): - converter_state = "true" # 转换wav成功 - else: - converter_state = "false" # 转换wav失败 - logger.info("[WX]receive voice converter: " + converter_state) + wav_file = os.path.splitext(silk_file)[0] + '.wav' + sil_to_wav(silk_file, wav_file) # 语音识别为文本 query = super().build_voice_to_text(wav_file).content # 交验关键字 @@ -183,21 +164,8 @@ class WechatyChannel(Channel): await voice_file.to_file(silk_file) logger.info("[WX]receive voice file: " + silk_file) # 将文件转成wav格式音频 - wav_file = silk_file.replace(".slk", ".wav") - with open(silk_file, 'rb') as f: - silk_data = f.read() - pcm_data = pysilk.decode(silk_data) - - with wave.open(wav_file, 'wb') as wav_data: - wav_data.setnchannels(1) - wav_data.setsampwidth(2) - wav_data.setframerate(24000) - wav_data.writeframes(pcm_data) - if os.path.exists(wav_file): - converter_state = "true" # 转换wav成功 - else: - converter_state = "false" # 转换wav失败 - logger.info("[WX]receive voice converter: " + converter_state) + wav_file = os.path.splitext(silk_file)[0] + '.wav' + sil_to_wav(silk_file, wav_file) # 语音识别为文本 query = super().build_voice_to_text(wav_file).content # 校验关键字 @@ -260,21 +228,12 @@ class WechatyChannel(Channel): if reply_text: # 转换 mp3 文件为 silk 格式 mp3_file = super().build_text_to_voice(reply_text).content - silk_file = mp3_file.replace(".mp3", ".silk") - # Load the MP3 file - audio = AudioSegment.from_file(mp3_file, format="mp3") - # Convert to WAV format - audio = audio.set_frame_rate(24000).set_channels(1) - wav_data = audio.raw_data - sample_width = audio.sample_width - # Encode to SILK format - silk_data = pysilk.encode(wav_data, 24000) - # Save the silk file - with open(silk_file, "wb") as f: - f.write(silk_data) + silk_file = os.path.splitext(mp3_file)[0] + '.sil' + voiceLength = mp3_to_sil(mp3_file, silk_file) # 发送语音 t = int(time.time()) - file_box = FileBox.from_file(silk_file, name=str(t) + '.silk') + file_box = FileBox.from_file(silk_file, name=str(t) + '.sil') + file_box.metadata = {'voiceLength': voiceLength} await self.send(file_box, reply_user_id) # 清除缓存文件 os.remove(mp3_file) @@ -337,21 +296,12 @@ class WechatyChannel(Channel): reply_text = '@' + group_user_name + ' ' + reply_text.strip() # 转换 mp3 文件为 silk 格式 mp3_file = super().build_text_to_voice(reply_text).content - silk_file = mp3_file.replace(".mp3", ".silk") - # Load the MP3 file - audio = AudioSegment.from_file(mp3_file, format="mp3") - # Convert to WAV format - audio = audio.set_frame_rate(24000).set_channels(1) - wav_data = audio.raw_data - sample_width = audio.sample_width - # Encode to SILK format - silk_data = pysilk.encode(wav_data, 24000) - # Save the silk file - with open(silk_file, "wb") as f: - f.write(silk_data) + silk_file = os.path.splitext(mp3_file)[0] + '.sil' + voiceLength = mp3_to_sil(mp3_file, silk_file) # 发送语音 t = int(time.time()) file_box = FileBox.from_file(silk_file, name=str(t) + '.silk') + file_box.metadata = {'voiceLength': voiceLength} await self.send_group(file_box, group_id) # 清除缓存文件 os.remove(mp3_file) diff --git a/voice/google/google_voice.py b/voice/google/google_voice.py index 2cc9851..8770b58 100644 --- a/voice/google/google_voice.py +++ b/voice/google/google_voice.py @@ -3,17 +3,14 @@ google voice service """ -import pathlib -import subprocess import time -from bridge.reply import Reply, ReplyType import speech_recognition import pyttsx3 from gtts import gTTS +from bridge.reply import Reply, ReplyType from common.log import logger from common.tmp_dir import TmpDir from voice.voice import Voice -from voice.audio_convert import mp3_to_wav class GoogleVoice(Voice): @@ -30,11 +27,10 @@ class GoogleVoice(Voice): self.engine.setProperty('voice', voices[1].id) def voiceToText(self, voice_file): - new_file = voice_file.replace('.mp3', '.wav') + # new_file = voice_file.replace('.mp3', '.wav') # subprocess.call('ffmpeg -i ' + voice_file + # ' -acodec pcm_s16le -ac 1 -ar 16000 ' + new_file, shell=True) - mp3_to_wav(voice_file, new_file) - with speech_recognition.AudioFile(new_file) as source: + with speech_recognition.AudioFile(voice_file) as source: audio = self.recognizer.record(source) try: text = self.recognizer.recognize_google(audio, language='zh-CN') From 5b85e60d5d5615fb5fb2bb82dfb7a2e17f59effe Mon Sep 17 00:00:00 2001 From: zwssunny Date: Mon, 27 Mar 2023 18:24:39 +0800 Subject: [PATCH 6/9] =?UTF-8?q?=E5=A2=9E=E5=8A=A0=E7=BE=A4=E7=BB=84?= =?UTF-8?q?=E8=AF=AD=E8=A8=80=E5=8A=9F=E8=83=BD?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- app.py | 6 +++--- bot/bot_factory.py | 6 +++--- config.py | 1 + 3 files changed, 7 insertions(+), 6 deletions(-) diff --git a/app.py b/app.py index 7d42b9d..c78a72c 100644 --- a/app.py +++ b/app.py @@ -1,6 +1,6 @@ # encoding:utf-8 -import config +from config import conf, load_config from channel import channel_factory from common.log import logger @@ -9,10 +9,10 @@ from plugins import * def run(): try: # load config - config.load_config() + load_config() # create channel - channel_name='wx' + channel_name=conf().get('channel_type', 'wx') channel = channel_factory.create_channel(channel_name) if channel_name=='wx': PluginManager().load_plugins() diff --git a/bot/bot_factory.py b/bot/bot_factory.py index 06df336..cf9cfe7 100644 --- a/bot/bot_factory.py +++ b/bot/bot_factory.py @@ -6,9 +6,9 @@ from common import const def create_bot(bot_type): """ - create a channel instance - :param channel_type: channel type code - :return: channel instance + create a bot_type instance + :param bot_type: bot type code + :return: bot instance """ if bot_type == const.BAIDU: # Baidu Unit对话接口 diff --git a/config.py b/config.py index 5732969..9b3204f 100644 --- a/config.py +++ b/config.py @@ -70,6 +70,7 @@ available_setting = { # chatgpt指令自定义触发词 "clear_memory_commands": ['#清除记忆'], # 重置会话指令 + "channel_type": "wx", # 通道类型，支持wx,wxy和terminal } From f76e8d9a77e9fb35ce22a64f5038dd8b7fa694ea Mon Sep 17 00:00:00 2001 From: zwssunny Date: Mon, 27 Mar 2023 18:25:54 +0800 Subject: [PATCH 7/9] =?UTF-8?q?=E6=A0=B9=E6=8D=AE=E5=8F=82=E6=95=B0?= =?UTF-8?q?=E5=88=9B=E5=BB=BA=E9=A2=91=E9=81=93?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- channel/wechat/wechat_channel.py | 2 +- channel/wechat/wechaty_channel.py | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/channel/wechat/wechat_channel.py b/channel/wechat/wechat_channel.py index 3d2c26a..c9a2255 100644 --- a/channel/wechat/wechat_channel.py +++ b/channel/wechat/wechat_channel.py @@ -190,7 +190,7 @@ class WechatChannel(Channel): thread_pool_callback) def handle_group_voice(self, msg): - if conf().get('speech_recognition') != True: + if conf().get('group_speech_recognition') != True: return logger.debug("[WX]receive group voice msg: " + msg['FileName']) group_name = msg['User'].get('NickName', None) diff --git a/channel/wechat/wechaty_channel.py b/channel/wechat/wechaty_channel.py index cc7788a..ac6717c 100644 --- a/channel/wechat/wechaty_channel.py +++ b/channel/wechat/wechaty_channel.py @@ -44,6 +44,7 @@ class WechatyChannel(Channel): async def on_scan(self, status: ScanStatus, qr_code: Optional[str] = None, data: Optional[str] = None): + pass # contact = self.Contact.load(self.contact_id) # logger.info('[WX] scan user={}, scan status={}, scan qr_code={}'.format(contact, status.name, qr_code)) # print(f'user <{contact}> scan status: {status.name} , 'f'qr_code: {qr_code}') From 1baf1a79e53bbdd57783e8e2079545e860eb3c9e Mon Sep 17 00:00:00 2001 From: zwssunny Date: Mon, 27 Mar 2023 19:38:19 +0800 Subject: [PATCH 8/9] =?UTF-8?q?=E5=90=88=E5=B9=B6=E5=86=B2=E7=AA=81?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- channel/wechat/wechat_channel.py | 29 ++++++----------------------- 1 file changed, 6 insertions(+), 23 deletions(-) diff --git a/channel/wechat/wechat_channel.py b/channel/wechat/wechat_channel.py index d0cd5ca..06a3381 100644 --- a/channel/wechat/wechat_channel.py +++ b/channel/wechat/wechat_channel.py @@ -52,10 +52,6 @@ def handler_group_voice(msg): WechatChannel().handle_group_voice(msg) return None -@itchat.msg_register(VOICE, isGroupChat=True) -def handler_group_voice(msg): - WechatChannel().handle_group_voice(msg) - return None class WechatChannel(Channel): @@ -114,7 +110,7 @@ class WechatChannel(Channel): context.kwargs = {'isgroup': False, 'msg': msg, 'receiver': other_user_id, 'session_id': other_user_id} thread_pool.submit(self.handle, context).add_done_callback(thread_pool_callback) -@time_checker + @time_checker def handle_text(self, msg): logger.debug("[WX]receive text msg: " + json.dumps(msg, ensure_ascii=False)) @@ -208,19 +204,6 @@ class WechatChannel(Channel): thread_pool.submit(self.handle, context).add_done_callback( thread_pool_callback) - def handle_group_voice(self, msg): - if conf().get('group_speech_recognition') != True: - return - logger.debug("[WX]receive group voice msg: " + msg['FileName']) - group_name = msg['User'].get('NickName', None) - group_id = msg['User'].get('UserName', None) - from_user_id = msg['ActualUserName'] - context = Context(ContextType.VOICE, msg['FileName']) - context.kwargs = {'isgroup': True, 'msg': msg, - 'receiver': group_id, 'session_id': from_user_id} - thread_pool.submit(self.handle, context).add_done_callback( - thread_pool_callback) - def handle_group_voice(self, msg): if conf().get('group_speech_recognition', False) != True: return @@ -303,19 +286,19 @@ class WechatChannel(Channel): os.remove(wav_path) os.remove(mp3_path) if reply.type != ReplyType.ERROR and reply.type != ReplyType.INFO: - context.content = reply.content # 语音转文字后，将文字内容作为新的context + content = reply.content # 语音转文字后，将文字内容作为新的context context.type = ContextType.TEXT if (context["isgroup"] == True): # 校验关键字 - match_prefix = self.check_prefix(context.content, conf().get('group_chat_prefix')) \ - or self.check_contain(context.content, conf().get('group_chat_keyword')) + match_prefix = self.check_prefix(content, conf().get('group_chat_prefix')) \ + or self.check_contain(content, conf().get('group_chat_keyword')) # Wechaty判断is_at为True，返回的内容是过滤掉@之后的内容；而is_at为False，则会返回完整的内容 if match_prefix is not None: # 故判断如果匹配到自定义前缀，则返回过滤掉前缀+空格后的内容，用于实现类似自定义+前缀触发生成AI图片的功能 prefixes = conf().get('group_chat_prefix') for prefix in prefixes: - if context.content.startswith(prefix): - context.content = context.content.replace( + if content.startswith(prefix): + content = content.replace( prefix, '', 1).strip() break else: From b3c8a7d8de3bf51440e1b079155622d7a894dd36 Mon Sep 17 00:00:00 2001 From: zwssunny Date: Mon, 27 Mar 2023 19:58:29 +0800 Subject: [PATCH 9/9] =?UTF-8?q?check=5Fprefix=E5=87=BD=E6=95=B0=E8=B7=91?= =?UTF-8?q?=E5=88=B0=E5=A4=96=E9=9D=A2=E4=BA=86?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- channel/wechat/wechat_channel.py | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/channel/wechat/wechat_channel.py b/channel/wechat/wechat_channel.py index 06a3381..cb75e94 100644 --- a/channel/wechat/wechat_channel.py +++ b/channel/wechat/wechat_channel.py @@ -290,16 +290,15 @@ class WechatChannel(Channel): context.type = ContextType.TEXT if (context["isgroup"] == True): # 校验关键字 - match_prefix = self.check_prefix(content, conf().get('group_chat_prefix')) \ - or self.check_contain(content, conf().get('group_chat_keyword')) + match_prefix = check_prefix(content, conf().get('group_chat_prefix')) \ + or check_contain(content, conf().get('group_chat_keyword')) # Wechaty判断is_at为True，返回的内容是过滤掉@之后的内容；而is_at为False，则会返回完整的内容 if match_prefix is not None: # 故判断如果匹配到自定义前缀，则返回过滤掉前缀+空格后的内容，用于实现类似自定义+前缀触发生成AI图片的功能 prefixes = conf().get('group_chat_prefix') for prefix in prefixes: if content.startswith(prefix): - content = content.replace( - prefix, '', 1).strip() + content = content.replace(prefix, '', 1).strip() break else: logger.info("[WX]receive voice check prefix: " + 'False')