Home » News » ElevenLabs Launches AI Voice Generator That Can Clone Your Voice in 30 Languages

ElevenLabs Launches AI Voice Generator That Can Clone Your Voice in 30 Languages

(Image Credit Google)
Image credit : Engadget The one-year old start-up ElevenLabs has truly exploited its potential of machine learning by creating its latest text-to-speech tool that supports 30 languages, 22 more languages than it did earlier, including Ukrainian, Korean, Swedish, Arabic, and more. Earlier, the synthesis model kicked off with a tool that generated speech just in English, which was further extended to Eleven Multilingual version 1, which used text inputs and AI voices to produce speech in six languages: English, Hindi, Polish, Spanish, French, Italian, Portuguese and German.  [caption id="attachment_191461" align="aligncenter" width="1280"]ElevenLabs AI voice clone Image credit : YouTube[/caption] However, after the launch of the Eleven Multilingual version 2, the model can now synthesize speech in 30 more languages, including Korean, Dutch, Turkish, Swedish, Indonesian, Vietnamese, Filipino, Ukrainian, Greek, Czech, Finish, Romanian, Danish, Bulgarian, Malay, Hungarian, Norwegian, Slovak, Croatian, Classic Arabic and Tamil. “ElevenLabs was started with the dream of making all content universally accessible in any language and in any voice,” ElevenLabs CEO and co-cofounder Mati Staniszewski said in a statement. “With this release, we’re one step closer to making this dream a reality and making human-quality AI voices available in every dialect. Our text-to-speech generation tools help level the playing field and bring top quality spoken audio capabilities to all the creators out there.”   [caption id="attachment_191464" align="aligncenter" width="1000"]ElevenLabs AI voice clone Image credit : MetaNews[/caption] With the release of Eleven Multilingual version 2 the tech start-up has made an official exit from the beta phase, enabling it for businesses and individuals looking to personalize their content for audiences all over the globe. It comes more than a month after ElevenLabs’ $19 million series A round that valued the company at nearly $100M. As per ElevenLabs, the recent Multilingual v2 model claims to provide “emotionally rich” audio in a total of 30 languages. The tech start-up has floated two AI voice synthesis tools, one is a text-to-speech model and the other is the “VoiceLab” that allows paid users replicate their voice by inputting their speech segments into the model to generate a type of voice clone. Using the v2 model, users can get these generated voices to start speaking in Greek, Malay, or Turkish. Also read : Google Pixel Call Screen Beta Adds AI Voices to Help You Screen Spam Calls In a text-to-speech model, the user has to input the text in the language of their choice, choose the voice they want (entirely new, synthetic or cloned) and tweak with a few speech settings & parameters. The model will by default recognize the written language and utilize the set parameters to produce speech in it. Additionally, it preserves the distinctive qualities of the chosen voice in all languages, including its original accent. 

By Awanish Kumar

I keep abreast of the latest technological developments to bring you unfiltered information about gadgets.


In the ever-changing world of technology and retai...


In a bid to capture the attention of users and dri...


Apple is preparing for a game-changing move with i...


Google has been making huge headways in artificial...


Elon Musk's artificial intelligence firm, xAI, is ...


In a digital showdown that has captured the attent...