Lyrebird | Create a digital copy of voice

This may not be directly useful at the moment, but it's too amazing not to feature, and once their API comes out of private beta, there are lots of potential applications. All you need to do to generate a digital copy of your voice, is to read about 30 sentences minimum. As an example, here is a sentence actually read out by me, and here is Lyrebird's synthesis of the same sentence (note: I never spoke that sentence, or even the words CrankWheel or marketing or company, to Lyrebird). The synthesized voice gets better as you read out more example sentences for Lyrebird to process, but the example I linked to was generated from the bare minimum of recordings.


Want to receive more content like this in your inbox?