Image: © Miljan Živković/Stock.adobe.com
A podcast episode originally recorded in English will soon be available in Spanish, French and German, while keeping the speaker’s original voice and style.
Spotify is rolling out a new voice translation feature that uses OpenAI technology to translate podcast episodes while keeping the original voice and style.
This means that podcast episodes currently available in English will soon be accessible in people’s native languages, starting with Spanish, French and German.
The latest Spotify tool leverages OpenAI’s newly released voice-generation technology to match the original speaker’s style, making for a “more authentic listening experience that sounds more personal and natural” than traditional dubbing.
“A podcast episode originally recorded in English can now be available in other languages while keeping the speaker’s distinctive speech characteristics,” the company wrote in its announcement yesterday (25 September).
For the pilot, Spotify has worked with podcasters Dax Shepard, Monica Padman, Lex Fridman, Bill Simmons and Steven Bartlett to generate AI voice translations for selected episodes in languages such as Spanish, French and German.
Starting with an initial bundle of episodes in Spanish, Spotify said it will roll out French and German translations “in the coming days and weeks”.
“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, vice-president of personalisation at Spotify.
“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.”
The translated episodes will be available to both Premium and free users across the world as part of the pilot. Spotify said the first set of episodes using the AI technology are available on a dedicated Voice Translations hub within its app.
Spotify has been investing heavily to integrate AI into its streaming service. Earlier this year, the Stockholm-based company revealed an AI-powered DJ that acts as a sort of virtual assistant to users listening to music through the app.
In January, Microsoft unveiled a text-to-speech AI model called VALL-E that it claimed can simulate anyone’s voice using only three seconds of audio.
10 things you need to know direct to your inbox every weekday. Sign up for the Daily Brief, Silicon Republic’s digest of essential sci-tech news.
