Knowledge Base

Getting Started

  • FAQ

     

    Table of contents:

    1. Can I select a different voice for each speaker?

    2. What languages are currently supported by KUDO AI?

    3. What is KUDO AI?

    4. How does KUDO AI work?

    5. Will this replace human interpretation?

    6. Shouldn't interpretation specialists like KUDO know better than to dabble in AI?

    7. Can I mix human interpreters and AI interpreters in the same meeting?

    8. Will this technology have access to specific glossaries and materials we upload? 

    9. What if the quality is not high enough? Can I get my money back?

    10. What is the overall level of accuracy we can expect? 

    11. How do I know that the results of the S2S translation are good enough when I do not understand the other languages? 

    12. If this offering is cheaper than using human interpretation service, what keeps clients from trying out KUDO AI for events in which they have previously used human interpretation?

    13. Does KUDO AI recognize dialects or various accents?

     

     

    Can I select a different voice for each speaker?

    Yes. When connecting to a meeting on KUDO using AI interpretation, you can choose between a female or a male voice. This choice is specific to each user logging in and can be updated anytime in the settings.

    ⚠️ if you’re having an on-site or hybrid event, this voice setting may need to be considered if all your tech team is using one single laptop to send the audio feed into KUDO.

     

     

    What languages are currently supported by KUDO AI?

    Source language is the language presenters will be speaking during the meeting. KUDO AI currently supports the following source languages:

    1. Brazilian Portuguese
    2. British English
    3. Canadian French
    4. English
    5. French
    6. German
    7. Italian
    8. Mexican Spanish
    9. Portuguese
    10. Spanish

    Target languages are the languages your audience will select and listen to the meeting into. KUDO AI currently supports the following target languages:

    1. Arabic
    2. Brazilian Portuguese
    3. Canadian French
    4. Chinese
    5. Chinese (Taiwan)
    6. Croation
    7. Czech
    8. Danish
    9. Dutch
    10. English
    11. Finnish
    12. French
    13. German
    14. Greek
    15. Hebrew
    16. Hindi
    17. Italian
    18. Japanese
    19. Korean
    20. Mexican Spanish
    21. Norwegian
    22. Persian (Farsi)
    23. Polish
    24. Portuguese
    25. Romanian
    26. Russian
    27. Spanish
    28. Swedish
    29. Turkish
    30. Ukrainian

    More languages are currently being developed and tested in beta versions. If you are interested in getting involved in the testing process, please reach out to your KUDO contact.

    You can select multiple source language if this option is activated in your account, and multiple target languages. For stability and performance's sake, we recommend you select a maximum of 10 target languages. This recommendation may vary depending on your meeting set up. For tailored advice, please reach out to your KUDO contact.

     

     

    What is KUDO AI?

    KUDO AI is a machine-powered, real-time speech translation solution. Developed in-house by a team with joint expertise in language and technology, the pilot version of this ground-breaking product was launched in Q1 2023 on the KUDO platform, making it the world’s first fully integrated, end-to-end solution of its kind.

    Given the potential for language access to transform the way we communicate, the product roadmap for KUDO AI—like that of all KUDO’s human interpretation tools and solutions—includes continuous optimizations. 

     

    How does KUDO AI work?

    As machine translation technology goes, the methodology of KUDO AI is also unique; it integrates state-of-the-art Natural Language Processing systems like speech recognition and synthesis with innovative KUDO language models trained to support real-time, continuous translation of spoken language. Essentially, KUDO AI goes a step further than the norm by analyzing speech structure in real time and breaking it down in a way that mimics a more natural pace of speaking. The result? A unique user experience that offers clients the ability to customize voices and even control speech fluency, based on KUDO Speedometer technology.

    While we are unable to divulge details about the single components and processes involved—which come under KUDO’s IP—we can share that the solution uses a robust cascading system comprising speech recognition, machine translation, speech synthesis, and modules to analyze the speech in real-time and make informed decisions on the translation strategies.

     

    Will this replace human interpretation?

    No. KUDO AI is not a replacement for our existing solution, but an expansion of language access to market segments that have never been able to afford professional interpretation. 

    Interpretation is a broad field spanning many use cases, objectives, and methods. Professional interpreters are needed to ensure accurate communication across languages, and they will be for years to come. Technology can be helpful in repetitive, scripted exchanges, however, and for languages that are widely spoken. This is not a zero-sum game. 

    Ultimately, language is complex, and it is questionable whether AI will ever be able to replace the judgment, flare, presence of mind, and the ability of a human interpreter to mediate complex philosophy or highly technical discussions. But as technology continues to evolve, so will interpreters’ roles.

     

    Shouldn't interpretation specialists like KUDO know better than to dabble in AI?

    The very fact that we are industry experts makes us the best company to launch an AI solution (best for both interpreters and clients). Whereas AI and technology-centric companies exist and are growing in number, KUDO AI is simply an addition or “entry point” to our existing interpretation offerings – one that moreover highlights the superior quality of professional interpreters across the industry by virtue of it being marketed as a “basic” solution.

     

    Can I mix human interpreters and AI interpreters in the same meeting?

    We are currently evaluating this option, but in the very first version of KUDO AI, it will not be possible to combine human interpreters with AI in the same meeting.  

     

    Will this technology have access to specific glossaries and materials we upload? 

     

    Yes. KUDO focuses on providing the most accurate interpretation to a specific customer conversation. This is the case with our human interpreters, and it will be the case for our AI solution. We aim to allow clients, if they wish, to integrate their own resources in order to increase the quality of translation for a specific event. 
    You can add a list of proper names (people's name, product's name, etc.) so that AI can use them to enhance quality. 

     

    What if the quality is not high enough? Can I get my money back?

    Extensive rounds of user testing indicate that KUDO AI is sufficiently good to be used in select meetings and events, even in its first version. Existing clients will additionally be provided with a test meeting so they can assess the quality for themselves. Based on what use cases they want to test, their client managers will then recommend whether KUDO AI is a good fit or not. 

     

    What is the overall level of accuracy we can expect? 

    Tests have shown that the accuracy level of KUDO AI – in the specific scenarios for which we have planned use cases for the solution – is on average 3.4/5, and that quality is 3.8/5. These scores were surprisingly high compared with human interpretation.

     

    How do I know that the results of the S2S translation are good enough when I do not understand the other languages? 

    This is a problem you would have with any language interpretation solution – human or AI. 

    Feedback from your meeting participants – during or after – should indicate the quality of both spoken and written translation provided by KUDO AI. And bear in mind that the KUDO team are, above all, experts in multilingual communication. Whether it is our human interpretation solution or our AI Speech Translator, we are constantly testing and optimizing our services. 
      

    If this offering is cheaper than using human interpretation service, what keeps clients from trying out KUDO AI for events in which they have previously used human interpretation?

    KUDO has designed a pricing model so that both KUDO AI and Human-powered Interpretation are available to the clients. Also, in its present form, KUDO AI presents several limitations that make it incompatible with certain use-cases, for which human interpretation remains the best fit. E.g., KUDO AI can only be used in non-interactive, unidirectional presentations where listeners are passive. For anything else, the use of human interpreters will be needed.

     

    Does KUDO AI recognize dialects or various accents?

    We plan to include cover for mainstream language variations, such as Brazilian Portuguese and Canadian French. As for accents, KUDO AI probably fares better than the average interpreter in accommodating them. Part of the reason is that, unlike a human interpreter, the technology has no bias and attaches no judgment to how a speaker enunciates their words.

  • Having a Multilingual Meeting Using KUDO AI: Best Practices

    Before the event 

     

    • Inform the KUDO team of any music that might be played during the event, as this can impact the quality of AI interpretation. 
    • Share a list of nouns, names, acronyms etc with the KUDO team to help the AI identify specific terms.
    • Let your speakers know that AI is optimized for one to many, meaning very dynamic conversations may need to be adapted.
    • For on-site events, we recommend a test meeting a few days before to check the audio quality and make sure there will be no echo or sound from the public (applause, laughter etc.) interfering with the speaker’s voice. 

      

    During the event 

     

    • Remind the speaker(s) to stick to the programmed spoken language.
    • Keep all the unused microphones OFF for optimal sound quality and interpretation accuracy.
    • Keep in mind your speech's pace by monitoring the speedometer icon at the bottom center of the screen on the KUDO platform.
    • Video feed is not mandatory. However, it is best for online participants to see the speaker(s) and the presentation to understand and engage. Please also note that if you are recording the meeting, KUDO will grab what is being shared on the platform (you will only have audio if you keep all cameras OFF). 
  • How to book meetings with KUDO AI (Free trial)

    KUDO AI Free trial includes:

    • 10 free meetings during a 30-day period
    • Up to 40 minutes per meeting
    • 20+ source and target languages
    • All meetings are held on the KUDO Meeting platform
    • Up to 25 participants per meeting

    If you are a current KUDO customer, please contact your KUDO Representative to receive your access.

     

    1. Start a free trial

    Go to the KUDO AI page and click on ‘Start a free trial’.

    Start your free KUDO AI trial

     

    2. Sign up

    You will then be taken to a sign-up page, where you will place your e-mail and agree to the terms and conditions.

    Sign-up page

     

    3. Confirm your account

    After signing up, an automated email is sent to your inbox. Click on the link in the email to log in to your KUDO AI account.

     

    4. Welcome to your KUDO AI account!

    On the top, a blue bar informs you how many meetings you have left in your free trial.


    Below you will see a 3-step guide on how to book meetings, hover over the cards to find more details, followed by an FAQ. If you need any further support, find the live chat at the bottom right of the screen and talk to our experts.

    KUDO AI Account Dashboard

     

    5. Start booking your meetings

    By clicking on 'Book a Meeting' you will be taken to the booking page.

    1. Fill out the date, time and duration of your meeting. Free trial meetings are capped at 40 minutes. Once you upgrade to a paid package, the limit will be increased to 6 hours.
    2. Select one source language. This refers to the language that all the attendees will be speaking during your meeting. You can only select 1 source language.
    3. Select one or several target languages. This refers to the languages you need the AI translation into. All the participants will be able to switch to any of these languages anytime throughout the meeting.
    4. Choose between a Male or Female AI voice for your meeting.

    Book a KUDO AI meeting

     

    6. Confirm your meeting details

    You will then be taken to the confirmation page. Review the meeting information and confirm the booking by clicking on "Book Meeting". There will be no charge. The meeting will be deducted from your 10-meeting free trial balance.

    Confirm your meeting details

     

    7. Meeting booked!

    A pop-up survey appears so you can provide KUDO with immediate feedback about the booking experience.

    Post-booking survey

     

    8. Add the meeting to your calendar

    Add the meeting to your Outlook or Google Calendar to share the invite with your participants.

     

    9. Meeting information

    Click on the "View your meeting" button, to see all your upcoming meetings booked. Here you will find the meeting link, which you can share with your participants, or add the meeting to your calendar directly.

     

    10. Edit a booked meeting

    Click on one of your upcoming meetings to:

    • Add new target languages to the meeting.
    • Copy the meeting link to share with your participants.
    • Cancel the meeting (no cancellation fee, the meeting is credited back to your free trial balance).

    Important note: once a meeting is booked, you cannot edit its date or time. You have to cancel the meeting entirely and manually delete the calendar invites you created on your Outlook/Google calendar, if any.

    Meeting details

     

    Enjoy the multilingual experience powered by AI!