ElevenLabs' Text-to-Speech AI Can Speak Using Your Own Voice Across 28 Languages

Pioneering AI voice cloning company Elevenlabs has introduced the powerful Multilingual V2 voice generation model. The V2 model supports 28 languages, including English and Chinese, accurately reproducing speaker accents and tones. It delivers emotionally rich speech in 28 languages, marking a milestone in the field of voice cloning, breaking language barriers, and achieving perfect human voice replication. In addition to mainstream languages, the V2 model supports Indian English, Italian English, and various accented regional languages.

This cloned voice can now be utilized across the extensive array of languages supported by the multilingual model, include Chinese, Korean, Dutch, Turkish, Swedish, Indonesian, Filipino, Japanese, Ukrainian, Greek, Czech, Finnish, Romanian, Danish, Bulgarian, Malay, Slovak, Croatian, Classic Arabic, and Tamil. These languages join the previously available ones like English, Polish, German, Spanish, French, Italian, Hindi, and Portuguese.

Using Multilingual v2 is simple: First choose a pre-made, cloned or custom voice and fine-tune it for elements like clarity and stability. These adjustments can be made in ElevenLabs' other product, Voice Lab. Then, enter text in any language, which the AI will instantly convert into downloadable spoken audio.

Unlike traditional TTS (Text-to-Speech) models, the V2 model can produce emotionally expressive speech, earning its reputation as the closest tool to real human voice. V2 finds application in content creation, voice acting for games, audiobooks, and more!