Spotify has announced that it is a testing a new AI voice feature for podcasters.
Through the new feature, podcasters will able to translate their podcast episodes into different languages, but in their own voice.
The new tool benefits from the recently released open-AI voice generation technology. Spotify, through the new technology, aims to match the original speaker’s style in its translated podcasts.
Spotify also hopes to achieve a more “authentic listening experience” compared to traditional dubbing that sounds less personal and natural.
The podcast episodes originally recorded in English are translated into other languages while keeping the speaker’s distinctive speech characteristics.
“By matching the creator’s own voice, Voice Translation gives listeners around the world the power to discover and be inspired by new podcasters in a more authentic way than ever before,” says Ziad Sultan, VP of Personalisation.
“We believe that a thoughtful approach to AI can help build deeper connections between listeners and creators, a key component of Spotify’s mission to unlock the potential of human creativity.”
For its initial testing, Spotify has collaborated with podcasters Dax Shepard, Monica Padman, Lex Fridman, Bill Simmons, and Steven Bartlett. Selected episodes of their podcast catalogue have been translated into Spanish, French, and German.
The episodes that have been translated using the tool so far are:
- Lex Fridman Podcast – “Interview with Yuval Noah Harari”
- Armchair Expert – “Kristen Bell, by the grace of god, returns”
- The Diary of a CEO with Steven Bartlett – “Interview with Dr. Mindy Pelz”
Spotify has said that the voice-translated episodes will be available to listen for premium and free users.
In a Linkedin post, Spotify Founder and CEO Daniel Ek said that along with new podcasts, they’ll also soon be rolling out more languages.