I asked this question in a different SE site, and I guess it could be asked here too.

The question goes like this:

Is there a tool that can be used to generate songs (only de human voice) from a text file in a similar way to how speech synthesizers do?

Such tool should be able to separate the words into syllables, using some meta notation, and also support intervals of silence, beside allowing to specify the pitch and duration of each note.

Here is an example of how the output might sound like.


Browse other questions tagged .