Move over, ElevenLabs. Korean researchers have launched the HierSpeech++ service, which clones voices – in English for now, but for free

by alex

You can try out HierSpeech++ on Hugging Face or download it locally from GitHub.

We are giving away Zbirnaia Ukrayina football t-shirt signed by Gravians for a donation of 200 UAH for ZSU. In the description of the donation, please indicate your mobile number so that we can be awarded a prize! Skin donations 200 UAH per donation +1 chance to win! Take your fate

To create audio, simply upload a voice sample and the text you want to voice.

HierSpeech++ is currently only available in English, but a multilingual model is planned to be launched in the near future.

Previously, AI startup ElevenLabs launched its own voice cloning service, which also allows you to generate audio using neural networks based on uploaded samples lasting several minutes. (At the beginning of the year, the company made its technology publicly available, which was immediately taken advantage of by Internet trolls – then they spread fake voices of celebrities on social networks who said offensive things, declared war or quoted Hitler).

READ
A star in the field of machine learning and computer vision, Andrei Karpaty, left OpenAI

You may also like

Leave a Comment