Spotify is debuting a voice translation mechanism for podcasts, powered by AI, that will translate podcasts into additional languages while maintaining the sound of the hosts’ original voices.
The Spotify-developed translation feature was built using OpenAI’s voice transcription tool Whisper, which can transcribe English and other languages into English. However, this feature will go beyond speech-to-text transcription, essentially cloning the speaker’s voice to reproduce the podcast in another language.
Spotify is launching the new feature by working with a small group of podcasters, including Dax Shepard, Monica Padman, Lex Fridman, Bill Simmons and Steven Bartlett. Spotify plans to expand the group to include “The Rewatchables” from The Ringer and its upcoming show from Trevor Noah.
Spotify will start by releasing a small group of translated episodes in Spanish, with French and German coming soon. The translated episodes will be available for premium and free users of Spotify.
“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,” Ziad Sultan, Spotify’s vice president of personalization, said in a statement. “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.”
Spotify will begin to roll out the feature to users on the Now Playing View of included episodes beginning Monday. The music streaming platform has also created a Voice Translations Hub, which will be updated as more content is added to the program.