Hey everyone,

I'm working on a content creation tool that needs to have an audio track featuring spoken word synced with the corresponding text (think of subtitles in a movie). I've had little success with google, though I'm not entirely sure what kind of keywords I should be looking for. So I'm wondering if anyone knows any good libraries that could handle this kind of thing. If such a thing does not exist, I may be able to just use a speech recognition library, so I'm open to suggestions in that area as well.
Also, it doesn't have to be perfect. I just need something that can roughly align the two, and someone can always go back in and tweak the alignment if needed.

Thanks!

I dont have an answer to that, I know of Microsoft speech API but there are no really good tutorials on using it. Which is supposed to be speech to text. But how much audio do you need to sync? If all else fails, can you not make a transcript and cut up your sentences by say no more than 15 or 20 words and then for each chunk find out at what second that first word in each chunk starts. So without speech to text that's about all you can really do.