语音转文本 API(非移动)
我正在尝试编写一个程序,通过麦克风接收用户的音频,然后将所说的内容转换为文本以进行进一步操作。
我知道谷歌有这样的东西,但它是为Android开发者准备的,我正在尝试做一些更像chrome扩展的东西(chrome扩展是我所设想的,但我对替代方案持开放态度)。
我已经研究过 Mac OSX NSSpeechRecognizer,但我需要更全面的东西,因为这需要您提前指定有限的语法。
我无法预期或预测我的用户会对着麦克风说些什么(但我可以假设这将是英语)。
I'm trying to write a program that takes in audio from the user via microphone, and then converts what's being said to text for further manipulation.
I know google has such a thing, but it's for Android developers, and I'm trying to make something more like a chrome extension (chrome extension is what I had envisioned, but I'm open to alternatives).
I've looked at the Mac OSX NSSpeechRecognizer, but I need something more comprehensive since this requires you to specify a limited grammer ahead of time.
I can't expect, or predict what my users will say into the microphone (but I CAN assume it will be English).
如果你对这篇内容有疑问,欢迎到本站社区发帖提问 参与讨论,获取更多帮助,或者扫码二维码加入 Web 技术交流群。
绑定邮箱获取回复消息
由于您还没有绑定你的真实邮箱,如果其他用户或者作者回复了您的评论,将不能在第一时间通知您!
发布评论
评论(1)
Google 有一个非官方 API,可以按照这篇文章中的描述使用:
http://mikepultz.com/2011/03/accessing- google-speech-api-chrome-11/
如果您正在编写 Chrome 扩展程序,您可能可以使用如下标记:
添加麦克风按钮并使用 google 云语音识别将用户所说的内容填充到文本框中。
Google have an unofficial API, which can be used as described in this post:
http://mikepultz.com/2011/03/accessing-google-speech-api-chrome-11/
If you're writing a chrome extension, you might be able to use a tag like:
which adds the microphone button and uses google's cloud speech-recognition to fill the text box with what the user says.