Microsoft has developed a new AI speech generator, VALL-E 2. It is a text-to-speech (TTS) generator that can reproduce the voice of a human speaker using just a few seconds of audio. It is the latest advancement in neural codec language models. But the new AI voice generator is convincing enough to be mistaken for a real person — at least, according to its creators.
Microsoft has developed a new AI speech generator, VALL-E 2. It is a text-to-speech (TTS) generator that can reproduce the voice of a human speaker using just a few seconds of audio. It is the latest advancement in neural codec language models. But the new AI voice generator is convincing enough to be mistaken for a real person — at least, according to its creators.