(Monday, 10 June 2024. New York City, NY) – With an increasing number of clients using KUDO AI Speech Translator each month, our Product and Engineering teams have been busier than ever this year bringing out features to keep up with demand. From new translation languages to revamped design, here are KUDO’s product updates from the first half of 2024.
Since launching KUDO AI in January 2023 as the world’s first integrated speech-to-speech translator, the goal of our R&D efforts has revolved around one key area: user experience. As AI continues its second explosive year of seeing new technology and trends enter the market, KUDO has incorporated the latest innovations into our solution while remaining consistently focused on delivering the best in fluency, accuracy, and low latency. It stands to reason that when it comes to translation languages, we take a ‘quality not quantity’ approach.
After popular demand, on the list of new AI languages are:
These languages were previously available in beta version, but have now been moved to regular translation languages available to all users. What does this mean? That they’ve passed our Language Technology team’s rigorous quality testing criteria and can be comfortably used to translate important subject matter.
With hundreds of experimental and beta languages in the product ‘oven’, you can expect a wave of new translation languages very soon. Currently, KUDO AI offers 43 languages.
Across every industry, we’re seeing a return to in-person communication. As a result, our most popular product this year has been our simple web-based solution for live events, meetings, and tour groups. This real-time solution allows attendees to scan a QR code to access either AI-translated or human-interpreted audio and captions on any device – no downloads or account creation necessary – making it the most flexible way for organizations to offer language accessibility.
As well as a quicker scan-to-access user journey, and the ability to select a different audio and captions language at the same time, captions are now scrollable to allow participants to track and access the full transcript.
And with the rising demand for languages such as Hindi, Arabic, and Japanese, the KUDO interface now displays translated text from right to left for all relevant languages.
Our native integration with Microsoft Teams has also had a revamp. This integration allows users to add live speech translation (human or AI-powered) seamlessly to their Microsoft Teams meetings and events. Among its improvements:
Part of what makes KUDO AI unique is the Patented process behind our AI engine. We have an entire team in-house dedicated to improving the quality and user experience of this solution every day, and most recently, they’ve achieved this by integrating Large Language Models (LLM) in a global first for real-time speech translation technology.
Innovation doesn’t come without its challenges. As Claudio Fantinuoli, KUDO’s CTO, explains: “Controlling the behavior of the LLM isn’t easy, especially when our objective is to keep latency to a minimum. The huge advantage of using LLM, however, is that it allows us to translate using context (what a person has said in the original language) which in turn improves the quality of translation (coherence and accuracy). Our R&D focus on LLM puts us in a great position to improve translation quality further in the future, which is always our main goal at KUDO.”
Last, but certainly not least. Until now, AI speech translation has globally been limited to one-to-many use cases like live events, conferences, trainings, and internal company announcements. This is principally due to the increased latency incurred through AI translation compared with human interpretation, which would make for a poor user experience if you tried to hold a multi-way conversation using an AI speech translator.
This month, KUDO AI will become available as a fully conversational translation solution as well, through a specialized form of real-time subtitles that can be chosen upon creating a meeting or event. Users will have the option to choose either a webinar-style, one-to-many setting when they create their meeting – in which case translated audio and captions will be activated – or a conversational setting in which case live subtitles will be activated.
Without the added translation of audio, this format reduces latency (the time it takes for a translation to be rendered) to the absolute minimum while prioritizing accuracy and fluency. This means that back-and-forth conversations in multiple languages can be followed in the language of the user’s choice in as close to real-time as possible, expanding the use cases for KUDO AI to popular requests like board meetings, interviews, focus groups, Q&A sessions, and interactive conversations.
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 www.kudoway.com.
Contact
Chloë Walford-Delahaye
chloe@kudoway.com
Another major upgrade for KUDO AI Speech Translator with the integration of a Large Language Model (LLM) for enhanced quality and usability.
KUDO rolls out its AI Engine v.2.0 for KUDO AI. This update is set to increase the accuracy of KUDO AI’s speech translation by up to 30%.
English US
