While I was voicing the pipes for a mechanical organ I noticed that when they were playing incorrectly they would sometimes make sounds quite similar to human speech. I wondered if it would be possible to make special speaking pipes and whether it would be possible to make them talk.

The result was the Talking Machine — an acoustic speech synthesizer.The speech sounds are produced using a flow of air and resonators just as in natural speech.The machine has 32 pipes, each one a simplified version of the human vocal tract. They reproduce the spaces which are formed in the mouth, nose and throat when we speak.The pipes are built according to measurements of X-Ray photographs taken of a person speaking. In other words, the E-pipe reproduces the narrow shape of the human mouth saying E, the OO- pipe has something like the small round OO-shaped lips and so on. S, F, Sh and similar sounds are produced by special whistles which reproduce the shapes made by the lips, tongue and teeth. The valves which control the flow of air are operated by a computer.

The machine is being taught to speak English — about 400 words so far — and a few words in other languages. For example, in Japanese it can speak a few polite phrases and can count to 100. It also recites concrete poems, for example, Canzone di Maggio by Giacomo Balla.