ElevenLabs introduces AI translation and dubbing function, which can retain the voice and emotion of the original speaker.

CTOnews.com, Oct. 11 (Xinhua)-- on Tuesday, AI text-to-speech company ElevenLabs launched AI dubbing (AI Dubbing), a feature that converts spoken content into another language while preserving the voice, language pattern, emotion and intonation of the original speaker.

According to officials, AI dubbing is designed to allow viewers around the world to enjoy their favorite content in their native language, which can be converted in just a few minutes.

AI dubbing combines ElevenLabs's multilingual speech synthesis, voice cloning, text and audio processing technologies to retain the nature of the original content when creating a translation.

At the press conference, Mati Staniszewski, CEO and co-founder of ElevenLabs, shared the negative experience of late-stage dubbing content in his childhood and how new technologies can solve the problem. "I grew up in Poland and every English movie we watch is dubbed by a narrator," Staniszewski said. "this means that every actor has the same voice, which greatly reduces the viewing experience. The release of artificial intelligence dubbing is our biggest step in removing the language barriers to these content and will help audiences enjoy whatever content they want, no matter what language they speak."

CTOnews.com noted that the AI dubbing feature currently supports more than 20 languages supported by the Eleven Multilingual v2 model Includes English, Japanese, Chinese, German, Hindi, French, Korean, Portuguese, Italian, Spanish, Indonesian, Dutch, Turkish, Filipino, Polish, Swedish, Bulgarian, Romanian, Arabic, Czech, Greek, Finnish, Croatian, Malay, Slovak, Danish, Tamil and Ukrainian.

AI dubbing is available to all users from today, depending on the number of characters you want to dub.