On Wednesday, Google translated Translatotron, an in-development speech-to-speech translation system.
It's not the first system to translate speech from one language to another, but Google designed Translatotron to do it something other systems can't: the original speaker's voice in the translated audio
In other words, the tech could make it sound like you're speaking a language you don't know – a remarkable step forward on the path Streamlined Speech
According to Google's AI blog, most speech-to-speech translation systems follow a three-step process. First they transcribe the speech. Translatotron, however, is part of this altogether process and instead converts the speech into a spectrogram, and image that depicts audio frequencies. The system then creates a new spectrogram, this time in the target language, which it uses to produce the new audio.
In theory, Translatotron will be much faster than other speech-to-speech translation systems since it has only one process rather than three. The use of spectrograms also makes it easier to retain elements of the original audio, such as the speaker's voice and cadence.
The system is not ready to roll out just yet ̵
More on translation tech : English as "The Global Language" Might End, Says Expert