Product Release

Multi-Speaker Mode Among Latest KUDO AI Features to Go Live

KUDO adds multi-speaker mode for speech translation, automatic language detection, more natural sounding AI voices, and the ability to customize translations with a glossary.

(Tuesday, 29 August 2023. New York City, NY) – In its latest round of upgrades, users of KUDO’s patented AI Speech Translator will benefit from a range of new features that continue to enhance quality and user experience. These include the ability to have more than one speaker of a different language taking turns to present, automatic language detection, more natural sounding AI voices, and the ability to customize translations in advance with a glossary.

Since launching KUDO AI Speech Translator in January 2023, R&D efforts at KUDO have shown no sign of slowing down. On the contrary, the solution has undergone a brand-new AI engine, gained a Patent, seen a dramatic increase in translation accuracy with the integration of Large Language Models (LLM), and now, it offers multi-speaker translation among other features to be announced. The objective of these efforts: for KUDO to lead the AI speech translation movement in quality, not quantity, of languages in which the captions and audio are available.

Here are the latest—and upcoming—features to expect for KUDO AI:

Multi-Speaker Mode

Until now, KUDO AI has only allowed for one presenter in one-to-many use cases such as webinars, All Hands meetings, and live events, where listeners can choose a language in which to hear a single speaker. Today, KUDO has expanded these possibilities with the introduction of multiple source (or “input”) languages, meaning that several speakers of different languages can be present on the floor at any one time – taking it in turns to speak.

At its current state of development, AI speech translation technology is still recommended to be used only in a one-to-many use case such as:

  • Presentations (events, Town Halls, etc)
  • Training or L&D
  • Webinars
  • And many more.

How does it work? Each speaker can select their preferred language either before or during the meeting. This feature ensures that speakers can actively participate in a single meeting while speaking different languages. Conversations flow seamlessly, with the only caveat being an “ordered” conversation format to accommodate system latency, which is the lowest among competitors thanks to our patented real-time, continuous translation solution. Additionally, to make the translated voice more authentic and relatable, the speaker can now choose their preferred gender. The result? A dynamic and hyper-realistic multi-speaker presentation.

Automatic Language Detection

Next on the list of KUDO AI upgrades is an auto-floor detection feature which matches the language of the speaker with that of the listener more effectively. If a user has selected that they wish to hear the meeting in Spanish, for example, and the speaker(s) or presenter(s) speak in Spanish at any point during the meeting, the listener will no longer see or hear the AI translation and will simply hear the speaker’s audio in Spanish—much in the way that movie subtitles work.

Custom Glossary

Continuing the theme of an enhanced user experience, users of KUDO AI will soon be able to make their AI-translated meetings more accurate with the launch of a Custom Glossary feature. What does this mean? That users who require speech translation while discussing a specific subject matter can enter a list of words, names, products, places, or acronyms that they wish to have translated in a specific way in advance, to ensure that KUDO AI translates them correctly. This will prove particularly reliable for events like medical conferences or product launches.

New AI Voices

And finally, among the next round of KUDO AI features to go live will be the rollout of new, more natural-sounding AI voices. This upgrade aims to improve the acoustic experience for users who are listening to translations during particularly long meetings and events.

Why the focus on user experience? On these upgrades, the KUDO team had this to say:

“At KUDO, we prioritize quality over quantity. Our primary focus is to offer high-quality simultaneous translations with low latency. As we continuously innovate, our commitment remains targeted on delivering the best possible quality”, comments KUDO’s CPO, Tzachi Levy. “Most importantly, we are taking the lead from our users themselves. Currently, we are testing the waters with experimental languages, for example, including Japanese and Polish”.

This quality-first strategy appear to be working; as of today, KUDO AI has over 2,500 users and an overall rating of 4.1/5 stars. And the team anticipates this number rising in line with their ambitious roadmap of upgrades and upcoming features between now and the end of the year.

About KUDO

KUDO is the world leader in providing real-time multilingual solutions that enable people to communicate effortlessly in any language⁠—on any platform. Their network of 12,000 professional language interpreters, combined with their ground-breaking Speech Translator, empower organizations of all sizes to collaborate more efficiently, with greater inclusivity, and on an international scale. KUDO Inc. is a New-York based technology start-up founded and managed by language and conferencing industry insiders seeking to create a world in which everyone has the power to understand and be understood in their own language. More info at


Chloë Walford-Delahaye

Related Product Releases