Spotify Introduces New AI Voice Translation That Can Clone Podcasters' Voices

Spotify has introduced an AI-driven feature aimed at translating podcasts into various languages using the original host's voice. This development uses OpenAI's voice generation technology, which has been described as capable of producing "realistic synthetic voices" based on only a few seconds of speech.

The primary goal behind this initiative is to enhance the podcast listening experience, preserving the unique speech characteristics of the original podcaster.

By utilizing OpenAI's cutting-edge voice generation tech, Spotify aims to maintain authenticity, allowing listeners to engage with content more naturally than conventional dubbing methods.

Spotify's AI Translation Tool

This new tool developed by Spotify leverages state-of-the-art advancements, incorporating OpenAI's recently unveiled voice generation technology. It ensures that the translated content mirrors the original speaker's style, leading to a more authentic listening experience that stays true to the podcaster's distinctive voice.

During the initial phase of this pilot, Spotify collaborated closely with renowned podcasters like Dax Shepard, Monica Padman, Lex Fridman, Bill Simmons, and Steven Bartlett.

Together, they worked on generating AI-powered voice translations in Spanish, French, and German for select catalog episodes and future releases. The plan is to extend this feature to other popular shows in the future.

Ziad Sultan, vice president of Personalization at Spotify, emphasized the significance of Voice Translation, stating that it empowers listeners worldwide to connect with new podcasters in an incredibly authentic manner.

"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," Sultan said in a press statement.

Voice-Translated Episodes on Spotify

Voice-translated episodes from the pilot creators will be accessible to Premium and Free users globally. Initially, a set of translated episodes in Spanish will be released, followed by French and German versions in the upcoming days and weeks.

Users can find these translations on the Now Playing View of supported episodes. Additionally, a dedicated Voice Translations Hub will be regularly updated with more voice-translated content over the coming months.

This introduction marks the initial phase of Spotify's efforts to enable creators to reach a broader global audience. The feedback from creators and listeners during this pilot phase will play a pivotal role in shaping future expansions and innovations.

With the podcasting community on Spotify continually growing, the platform, with more than 100 million regular listeners, said it will explore novel ways to break down barriers in storytelling.