Spotify tests new AI feature: clones podcaster's voice and translates it into other languages

IT House reported on September 25 that Spotify is testing a new artificial intelligence feature called "Voice Translation", which can clone the podcast host's voice and use that voice to use another voice. A language readout podcast.

The tool, developed by Spotify with the help of OpenAI’s automatic speech recognition (ASR) system Whisper, uses a speech-to-text generation AI model to translate audio files and a speech copy model to match the style of the original speaker.

IT House noticed that the first hosts to participate in this new feature include Dax Shepard, Monica Padman, Lex Friedman, Bill Simmons and Steve Vin Bartlett. However, not every episode of their respective podcasts will be immediately available in multiple languages, and only Spanish translations are currently available

Spotify says more episodes will be available in the coming days and weeks, and French and German translations will also be available

The above is the detailed content of Spotify tests new AI feature: clones podcaster's voice and translates it into other languages. For more information, please follow other related articles on the PHP Chinese website!