ElevenLabs Unveils Multilingual v2: A Game-Changer in AI Speech Technology

ElevenLabs, a leading voice AI software company, has made a significant stride in its mission to eliminate linguistic barriers to content. The company has launched Eleven Multilingual v2, a revolutionary deep learning model that supports multilingual capabilities across 28 languages. This advancement is set to dramatically improve the accessibility of content for media companies, game developers, publishers, and independent creators worldwide.

The Eleven Multilingual v2 model is capable of producing ‘emotionally rich’ AI audio in nearly 30 languages. When text is inputted into the ElevenLabs text-to-speech platform, the new model can automatically identify almost 30 written languages and generate speech in them with an unprecedented level of authenticity. Regardless of whether a synthetic voice or cloned voice is being used, the speaker’s unique voice characteristics are maintained across all languages, including their original accent. This means the same voice can be used to bring content to life across 28 separate languages.

The languages supported by the multilingual model now include Chinese, Korean, Dutch, Turkish, Swedish, Indonesian, Filipino, Japanese, Ukrainian, Greek, Czech, Finnish, Romanian, Danish, Bulgarian, Malay, Slovak, Croatian, Classic Arabic, and Tamil. They join previously available languages including English, Polish, German, Spanish, French, Italian, Hindi, and Portuguese.

This release follows the public availability of Professional Voice Cloning to all creators on the platform. This feature allows users to create a perfect digital copy of their own voice, one that’s virtually indistinguishable from the original.

The launch of Eleven Multilingual v2 marks the official end of the company’s Beta phase, a pivotal moment in the company’s dedication to providing reliable and cutting-edge tools for its 1 million+ global users.

Looking ahead, ElevenLabs plans to introduce a mechanism that allows users to share voices on the platform and benefit from the development of new audio, fostering opportunities for human-AI collaboration.

The multilingual speech generation tool provides new opportunities for independent game developers and publishers to translate game experiences and audio content for international audiences. Educational institutions can provide learners with accurate audio content in target languages instantly, bolstering language comprehension and pronunciation skills.

Creators of all types can use ElevenLabs’ tool to improve content accessibility for people with visual impairments or additional learning needs by supplementing visual content with speech available in multiple languages.

In conclusion, the launch of Eleven Multilingual v2 is a significant step forward in ElevenLabs’ mission to make all content universally accessible in any language and in any voice. This technology is set to revolutionize the way we interact with content, breaking down linguistic barriers and fostering greater creativity, innovation, and diversity.

Original blog post can be found here : ElevenLabs Comes Out of Beta and Releases Eleven Multilingual v2 - a Foundational AI Speech Model for Nearly 30 Languages