Spotify is introducing an AI-powered Voice Translation tool for podcasts, allowing podcasters to translate their episodes into other languages using their own voice. This groundbreaking technology aims to create a more authentic and natural listening experience for audiences around the world. Spotify has collaborated with notable podcasters to generate AI-powered voice translations in languages such as Spanish, French, and German. The tool is set to expand to include other popular shows and will be accessible to both Premium and Free users.
The Voice Translation tool leverages the latest innovations in AI, including voice generation technology from OpenAI. The tool allows Spotify to match the original speaker’s style, ensuring a personalized experience. OpenAI’s ChatGPT, which can now see, hear, and speak, powers the voice generation capability of the tool. To create the voices, OpenAI collaborated with professional voice actors and used Whisper, its open-source speech recognition system.
Spotify’s pilot voice-translated episodes will be available globally, and the company plans to release an initial bundle of translated episodes in Spanish, with French and German translations following. This new AI tool is part of Spotify’s commitment to empowering creators and deepening connections between listeners and podcasters. It marks the company’s latest venture into AI-powered audio, following the launch of an AI ‘DJ’ feature earlier this year. Many industry professionals are now curious about when similar technology will be used on a large scale for artists, allowing them to release multilingual tracks in their own voices.