Meta's latest AI suite makes speech translation more seamless and expressive

Back in August, Meta unveiled its multimodal AI translation model, SeamlessM4T, which supports nearly 100 languages for text and 36 for speech. With an updated "v2" architecture, the tech giant is now expanding on this tool to make conversational translations more spontaneous and expressive — the latter a missing key to an authentic conversation across languages.

The first of the two new features is "SeamlessExpressive" which, as you can tell by the name, ports your expressions over to your translated speech. These include your pitch, volume, emotional tone (excitement, sadness or whispers), speech rate and pauses. Considering how translated speeches had always sounded robotic until now, this breakthrough is potentially a game-changer — both in our daily lives and also in content production. Supported languages include English, Spanish, German, French, Italian and Chinese, though the demo page is missing Italian and Chinese at the time of writing this article.

The second feature is "SeamlessStreaming," which starts translating a speech while the speaker is still talking, thus allowing others to hear a translation faster. There's still a short latency of just under two seconds, but at least you won't have to wait until someone finishes a sentence. According to Meta, the challenge here is that different languages have different sentence structures, so it had to develop an algorithm dedicated to studying partial audio input, in order to decide whether there's enough context to start generating a translated output, or whether to keep listening.

Meta's latest development on this "Seamless Communication" suite seems to be an impressive one — more so than the mobile interpreter tools offered by the likes of Google and Samsung. There's no word on when the public will be able to utilize these new features, but I can already imagine Meta baking them into its smart glasses some day, making them even more practical than ever.

This article originally appeared on Engadget at https://www.engadget.com/metas-latest-ai-suite-makes-speech-translation-more-seamless-and-expressive-060043686.html?src=rss https://www.engadget.com/metas-latest-ai-suite-makes-speech-translation-more-seamless-and-expressive-060043686.html?src=rss
Vytvořeno 1y | 4. 12. 2023 4:30:16


Chcete-li přidat komentář, přihlaste se

Ostatní příspěvky v této skupině

Doctor Who ‘The Story and the Engine’ review: Just a trim, thanks

Spoilers for “The Story and the Engine.”

Doctor Who lives and dies by the quality of its writing and acting far more than almost anything else on TV. Audie

10. 5. 2025 20:10:04 | Engadget
Your PS5 now natively accepts Apple Pay

As first reported by 9to5Mac,

10. 5. 2025 20:10:03 | Engadget
The developers behind Overwatch have unionized

Activision Blizzard’s Overwatch team has formed a wall-to-wall union under the Communications Workers of America (CWA). The union, which has been recognized by parent company Microsoft, includes ne

10. 5. 2025 17:41:10 | Engadget
Nintendo grants itself the power to brick Switches with pirated games

Nintendo’s latest legal move to combat piracy may be super effective. According to a new change in the Nintendo User Agreement, the console maker can brick your

10. 5. 2025 17:41:09 | Engadget
FDA approves at-home pap smear alternative device for cervical cancer screening

The Food and Drug Administration has

10. 5. 2025 17:41:08 | Engadget
Mexico is suing Google over 'Gulf of America' name change for US users

The Mexican government has filed a lawsuit against Google for renamin

10. 5. 2025 15:20:14 | Engadget