Spotify Is to Partner with OpenAI in Cloning Podcasters’ Voices

Spotify is to partner with OpenAI in cloning podcasters’ voices and then translate them into other languages reportedly. The partnership in question will allow podcasters to replicate their voices effectively to create foreign language versions of their shows automatically.

Spotify To Partner with OpenAI

Spotify To Partner with OpenAI

What if it is that podcasters could flip a switch and then speak another language instantly? That is the premise that is behind the new AI-powered voice translation feature of Spotify, which reportedly reproduces podcasts in other languages making use of the voice of the podcaster.

The company has just recently partnered with a handful of podcasters in a bid to translate their English-language episodes into Spanish with its new tool, and it also has plans to roll out French and German translations in the next couple of weeks. The initial batch of episodes as you should know will come from some big names, and this is inclusive of Dax Shepard, Monica Padman, Lex Fridman, Bill Simmons, and Steven Bartlett. Spotify also plans to expand the group in question to include The Rewatchables from The Ringer as well as its upcoming show from Trevor Noah.

Voice Transcription Tool of OpenAI Whisper

The backbone of the whole translation feature is the voice transcription tool of OpenAI Whisper, which can both transcribe English speech and then translate other languages into English easily and effectively. But the tool of Spotify goes way and well beyond speech-to-text translation as the feature in question will help to translate a podcast into a different language and then reproduce it in a synthesized version of the voice of the podcaster.

What Spotify Has To Say about the New Development

“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,” Spotify’s vice president of personalization, Ziad Sultan, in a statement stated.

OpenAI is very much likely behind the voice replication part of this new feature, too. The AI Company is at the moment making a couple of announcements this morning, and this is inclusive of the launch of a tool that can create “human-like audio from just text and a few seconds of sample speech.” OpenAI has stated that it is intentionally limiting just how widely this very tool will be available due to concerns surrounding safety and privacy.

Future Plans for the AI Tool

That is probably just part of the reason as to why Spotify says the translation tech in question is only being tested with a “select group” of podcasters for now. The company also did not elaborate on just how widely it planned to make the tool available or when it is users are to expect an expansion.

MORE RELATED POSTS

Check This Out Also:

LEAVE A REPLY

Please enter your comment!
Please enter your name here