ElevenLabs releases Eleven Multilingual v2: A speech-based artificial intelligence model supporting 30 languages

ElevenLabs recently released Eleven Multilingual v2, a multilingual voice generation model that enables the creation of "emotionally rich" AI audio in nearly 30 languages. This work will allow producers to localize audio for markets in Europe, Asia and the Middle East.

The research team spent 18 months studying indicators of human speech and developed new methods to identify context, express emotions when generating speech, and synthesize new, characteristic voices. The model automatically recognizes about 30 written languages and generates a voice in them with an unprecedented level of fidelity when entering text into the ElevenLabs text-to-speech platform.

The cloned or synthetic voice retains the characteristic features of the narrator's voice, such as his or her native accent, in all languages. You can now use the same voice to animate material in 28 languages.

This launch comes after the platform made it possible for all authors to use professional voice cloning. Users can now create digital copies of their voice that are virtually indistinguishable from the original, thanks to this update that was released along with security and safety improvements. In addition to existing languages (English, Polish, German, Spanish, French, Italian, Hindi and Portuguese), the new model also supports Chinese, Korean, Dutch, Turkish, Swedish, Indonesian, Filipino, Japanese, Ukrainian, Greek, Czech, Finnish, Romanian, Danish, Bulgarian, Malay, Slovak, Croatian, Classical Arabic and Tamil.

ElevenLabs has confirmed that the platform is coming out of beta today following the introduction of new features and ongoing improvements. This change is a watershed moment in the company's quest to provide more than 1 million users worldwide with reliable and up-to-date resources.

ElevenLabs is also working on a method that will allow users to collaborate with artificial intelligence to create new audio recordings using the platform.

By adding text to speech in many languages to visual content, the app makes it more accessible to people with visual impairments or other learning requirements. Below are some examples

• The multilingual speech generation tool opens up new opportunities for indie game developers and publishers to translate game experiences and audio content for international audiences, allowing them to communicate with players and listeners in their languages without sacrificing quality and accuracy.
• In addition, institutions now have the resources to provide timely access to high-quality audio materials in target languages that improve listening and pronunciation, as well as meet the different learning preferences of international students.

By reducing the time and cost of creating high-quality audio in multiple languages, ElevenLabs helps companies and authors create more original and accessible content that people of all backgrounds and languages can understand.