In the Bell Laboratories there is the converse of this machine, called a Vocoder. The loudspeaker is replaced by a microphone, which picks up sound. Speak to it, and the corresponding keys move.
From a linguistic standpoint, this is interesting, knowing how speech-to-text programs still make mistakes in trying to decipher what a person is saying, and the issues that have arisen continuously with differing dialects and the varied phonological inventories of different languages.