nanny cam with voice recognition tech?

Is it plausible that there could be software that could translate the audio on a nanny cam to text (voice recognition text)? Would this be expensive? Would someone be able to see it on their laptop, with wireless?

I'm guessing that you would need multiple high-quality microphones plus really good software for this to work with even 90% accuracy. Yeah, spendy.

There's no off the shelf solution, where you just open up the laptop, click an icon and get a neat transcription of the output of your nannycam. Doesn't mean it's not possible though.

There's a few dozen different speech-to-text software out there, dragon naturally speaking is the most famous, and I believe that some versions have the ability to process an arbitrary sound file. There's also nanny cams that offer web access for both voice and sound, and software that lets you turn any webcam into a nanny cam. Accuracy goes down depending on sound quality, and often completely out the window when accents are involved (Siri doesn't work with bostonites or scotsmen, for instance). You will need a decent quality microphone, but most voice recognition software has sound processing options for noisy environments. If the person with the nanny cam is a programmer or can afford the dev costs, programming a custom application that takes the output of the webcam/microphone and pushes it to a speech-to-text engine wouldn't be that difficult.

Thanks, the user is a 13 year old kid who is proficient with tech, and also deaf. If that makes any difference. He is using it to help his mother keep an eye on his accident prone grandfather while his mother is away, so he doesn't have to follow the old man around all the time. They're not rich, so the kid may have come up with a cheap DIY solution. Not sure if it would be in every room though.