Originally published at https://rohantechofficial.com/tech-news/amazon-polly-voice-cloning/
Amazon Polly, AWS's text-to-speech service, has a new trick: it can now clone a voice. Announced on November 19, voice cloning is generally available in Polly as a gated release, letting organisations build a custom synthetic voice from a few minutes of a speaker's recordings.
The pitch is brand consistency. Instead of a different stock voice in each product, a company can have one voice across its app, its phone support and its training videos — a voice customers learn to recognise as the brand itself.
Here is how it works. You submit between one and ten recordings, up to 15 minutes of audio in total, and Polly builds the voice model in about five to ten minutes. Creating the voice is free; you pay only when you generate speech with it, under Polly's standard pay-as-you-go pricing for the Generative engine.…