The SampleSumo MeloTranscript web service is a web service for transcribing monophonic melodies (recorded in an audio file) into a sequence of notes. Basically, you give it a sound file with a vocal melody, and the web service gives you back a start time, end time, average pitch, and amplitude for each detected note in the sound file.
It was mainly built for use with vocal melodies (singing, humming, singing with dadada, fafafa, etc...). With other monophonic material, your miles may vary. It will not work on polyphonic material like a full mix of several instruments, or a song from your music library, ... (although the results you will can be pretty funny sometimes).
Note that for most people their voice isn't a "fixed tuning" instrument, which means that most of the time, the detected frequencies will not perfectly fit the chromatic scale with a reference note A4 at 440 Hz. Take that into account when handling the results (just rounding to the nearest MIDI note might not always give the desired results). It might be usefull to provide some reference tone or background track to sing to, to alleviate this problem. Also, if the relative pitch distances are stable, one simple thing you could do is take the average of the deviations of the pitches from a perfect chromatic scale, and then subtract that average from all pitches, as some kind of "reference tuning correction".
SampleSumo combines music software development, intelligent audio processing, web technologies and hands-on experience with music creation tools to build solutions for end-users (musicians, gamers, producers, ...) and media-industry companies. More info on our company website.