苹果、微软的ai电脑已经可以语音操控电脑了。开源的也有,下面是一个开源的python+openai api实现windows语音交互沟通,让ai人工智能识别你的命令进行电脑关机和其他操作,示例代码如下:
# -*- coding: utf-8 -*- import speech_recognition as sr import pyttsx3 import openai import os import sys openai.api_key = "<your-api-key>" # 创建 TTS 对象 engine = pyttsx3.init() # 创建 Recognizer 对象 r = sr.Recognizer() def getopenairesponse(keyword): response = openai.Completion.create( engine="text-davinci-003", prompt=keyword, max_tokens=1024, temperature=0.5 ) return response["choices"][0]["text"] def listen_for_wake_word(): with sr.Microphone() as source: r.adjust_for_ambient_noise(source) print("等待唤醒词...") audio = r.listen(source) try: text = r.recognize_sphinx(audio, language='zh-CN') return text.lower() except: return "" def shutdown_computer(): print("电脑即将关机") engine.say("电脑即将关机") engine.runAndWait() if sys.platform == "win32": os.system('shutdown /s /t 1') else: os.system('sudo shutdown -h now') def restart_computer(): print("电脑即将重启") engine.say("电脑即将重启") engine.runAndWait() if sys.platform == "win32": os.system('shutdown /r /t 1') else: os.system('sudo reboot') is_active = False while True: if not is_active: wake_word = listen_for_wake_word() if "开机" in wake_word: is_active = True print("系统已开启") engine.say("系统已开启") engine.runAndWait() continue # 使用麦克风录音 with sr.Microphone() as source: r.adjust_for_ambient_noise(source) # 噪音抑制 print("我在听,您请说:") audio = r.listen(source) # 将语音转成文本 try: text = r.recognize_sphinx(audio, language='zh-CN') print("你说的:" + text) if "关闭系统" in text.lower(): is_active = False print("系统已关闭") engine.say("系统已关闭") engine.runAndWait() continue elif "关机" in text.lower(): shutdown_computer() break elif "重启" in text.lower(): restart_computer() break # 将文字转成语音并播放 response = getopenairesponse(text) engine.say(response) engine.runAndWait() except sr.UnknownValueError: print("识别失败") except
网友回复
腾讯混元模型广场里都是混元模型的垂直小模型,如何api调用?
为啥所有的照片分辨率提升工具都会修改照片上的图案细节?
js如何在浏览器中将webm视频的声音分离为单独音频?
微信小程序如何播放第三方域名url的mp4视频?
ai多模态大模型能实时识别视频中的手语为文字吗?
如何远程调试别人的chrome浏览器获取调试信息?
为啥js打开新网页window.open设置窗口宽高无效?
浏览器中js的navigator.mediaDevices.getDisplayMedia屏幕录像无法录制SpeechSynthesisUtterance产生的说话声音?
js中mediaRecorder如何录制window.speechSynthesis声音音频并下载?
python如何直接获取抖音短视频的音频文件url?