Is there software that outputs speech-to-text at the Phonological level?

Is there any software out there capable of taking audio files and outputting phonological (IPA) text?

I understand much of the software out there takes it straight to a language, but is there one that is 'teachab开发者_如何转开发le'?

CMU Sphinx might be able to do what you want. There are a few different versions, but the one I'm familiar with is Sphinx 3. In the FAQ it says you can get phone segmentations by making your "words" be individual phones (they're not IPA, though).

I'm almost certain SIL built something close to this, however, I can't remember what it was called, and I can't find any mention of it on the site. You might contact them directly.