Spotify is introducing a new AI-powered Voice Translation tool that can translate podcasts into different languages while preserving the original podcaster’s voice. The tool, described as “groundbreaking,” aims to provide a more authentic listening experience by matching the original speaker’s style. As part of a pilot program, Spotify has collaborated with several podcasters to generate AI-powered voice translations in languages such as Spanish, French, and German. The company plans to expand the tool to include other shows in the future.
The new tool leverages the latest innovations in AI, including voice generation technology from OpenAI, the creator of ChatGPT. OpenAI’s new voice capability allows the AI to see, hear, and speak, using text and a few seconds of sample speech to generate human-like audio. The voices used in the tool were created in collaboration with professional voice actors, and it also utilizes Whisper, OpenAI’s open-source speech recognition system, to transcribe spoken words into text.
Spotify will make the voice-translated episodes available worldwide to both Premium and Free users. Starting with Spanish, the company plans to release an initial bundle of translated episodes, with French and German translations following soon after. Spotify sees this tool as just the beginning of its commitment to using AI to empower creators and deliver their storytelling to a global audience. This new AI translation tool builds upon Spotify’s previous ventures into AI-powered audio, such as its AI ‘DJ’ feature and its acquisition of AI voice startup Sonantic.
