Run a meeting in 3 languages at once.
Let people speak in the language in which they do their best thinking. Run a meeting where, for example, one colleague speaks English, another Spanish, and another French, while each hears the conversation in their preferred language. The right setup depends on your meeting platform, licenses, and the three languages you need.
Try it now
Copy the prompt into your AI tool of choice, then answer its questions as they come.
Paste it into any AI chat to start. For most people, this is all you need.
Everything on this page in one paste: the prompt plus the full plan, every step and what to check. Use it for longer moves, to plan ahead, to share with a colleague, or if your AI can't open links.
How to run it
Choose a real conversation with participants who use three languages. Agree which language each person wants to speak and hear. Decide whether they need translated audio or whether reading translated captions would work for this meeting. The AI-help prompt below can find your current company options and guide the entire setup.
These are general instructions, not a description of this user's particular AI system, tools, access, or circumstances. Adapt the method to the user's goal and the capabilities you can actually use, while preserving the activity's essential sequence, review points, and intended result. ### Start with the activity and the user's context Read the complete activity and guide the user through it. Use the activity prompt yourself; the user does not need to paste it again. Keep the responsibilities of the user, the AI, and any colleague clear. Begin with what the user has already supplied. Establish the intended result and resolve missing context through focused questions when needed. Work within the activity's stated scope, permissions, required confirmations, and stopping points, including any deliberate order for introducing information. Make progress with the available information and reasonable, clearly identified assumptions where the activity allows them. ### Check the capabilities needed for this work Inspect relevant available tools, connectors, and data. Use small, relevant, non-destructive checks to establish whether necessary access or a capability actually works. Naming a product does not establish access to it. Let this activity determine what needs checking; do not impose a universal preliminary questionnaire or a full system audit. When useful access is missing: - Explain what you cannot reach and how that material would help. - Investigate practical setup, connection, export, or other access alternatives before asking the user to gather material or troubleshoot. - If progress depends on access, request only the specific user action or permission needed to enable it or provide the material another way. Continue useful independent work while awaiting the response. - Offer to walk the user through an export or upload. Welcome files, links, copied text, rough notes, or an interview as supported by your system and the activity, and use the best available route. If the missing access is optional, continue with what is available. ### Ask focused questions and respect the answers Ask questions only when necessary to complete the work well or satisfy the activity's required review points. Build on answers already supplied. Ask one question at a time, or a small group of closely related questions. Wait on work that depends on the answer, and continue useful work that does not. Explain unfamiliar language with examples where helpful. Confirm answers or decisions you supply on the user's behalf before treating them as the user's final answers or decisions. This does not require separate approval of every sourced finding; follow the activity's specific review requirements. ### Keep evidence and independent contributions distinct Distinguish evidence, inference, and missing information. Check your work against the source material. Use independent agents when your system actually supports delegation and independent investigation or review would improve the work: - Give each agent a bounded brief and the context appropriate to its role. - Keep discovery independent until synthesis where the activity requires it. Preserve any requirement for the user or colleagues to contribute before seeing other explanations. - Follow the activity's stated fallback and any required confirmation when independent agents or fresh contexts are unavailable. Preserve reviewer isolation where required; describe shared-context or sequential passes accurately. ### Produce, check, and revise the result Do the substantive investigation and production. Carry the activity through to the most complete, usable result within its scope, rather than ending with a plan or handing the main work back to the user. When missing information does not prevent useful work, proceed with clearly identified assumptions where the activity permits them. Check the result against the activity's completion criteria. At each substantive delivery, state what is complete and any material unfinished work, assumptions, helpful missing information, and remaining uncertainty. Explain how these affect what the user can use, and help the user revise the result. Preserve the activity's stopping point. Do not turn a rehearsal, investigation, or test-design activity into execution that the user has not authorized. Help me run a real meeting in three languages, using tools my company can actually use. Start with the meeting software and licenses we already have. Research current capabilities and guide setup and a short rehearsal before the real meeting. ### Understand the meeting and find our existing setup Use any meeting link, project name, or other context I have supplied. Inspect available calendar access for the meeting, attendee list, organizer, platform, and meeting type. Search relevant internal IT help pages, software catalogs, license records available to me, and support messages for translation features, approved meeting apps, and who can enable them. Search the related agenda, emails, chats, prior transcripts, and project documents for meeting purpose, terminology, names, and decisions people need to discuss. Explain which records you could actually access. Use these records to establish the people and their roles. Do not infer their preferred language from nationality or surname. Confirm the three spoken/listening languages, who needs which, whether participants are external, and whether they are using computers, phones, or meeting-room devices. Ask one focused question at a time only for consequential missing information. Clarify whether everyone needs translated speech in their ears, or whether translated captions would meet their needs. Treat three-language spoken interaction as the original target. If only captions or sequential two-language interpretation are available, explain that changed experience and wait for my choice. ### Research today's workable routes Browse current primary documentation and official integration listings. Date your findings. Check our platform first, then useful alternatives or approved add-ons. Investigate Microsoft Teams Interpreter, Zoom Voice Translator, Webex translation, Google Meet Speech Translation, and Wordly or KUDO only as relevant to our actual languages and setup. Verify all of the following for each serious candidate: - Actual spoken audio versus captions or translated transcripts. - Three languages in the same meeting, including each person replying in their own language; a list of supported languages alone is not enough. - Host and attendee license requirements, guest access, device support, administrator controls, and any regional or account rollout limits. - Native feature, installable app, additional browser page, bot participant, or custom integration; where each person hears the output. - Current setup instructions, known delay or language-switching behavior, and price or usage allowance when publicly established. Distinguish a quoted enterprise price from public list pricing and leave unknown charges unknown. Starting references, to recheck rather than assume current: - Teams: https://support.microsoft.com/en-us/teams/copilot/interpreter-in-microsoft-teams-meetings-and-calls - Zoom: https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0084896 - Webex: https://help.webex.com/en-us/article/7dzhht/Real-Time-Translation-in-Webex-Meetings-and-Events - Meet: https://support.google.com/meet/answer/16221730?hl=en - Wordly: https://help.wordly.ai/what-is-meeting-bot - KUDO: https://support.kudoway.com/hc/en-us/articles/40489091825047-Adding-KUDO-app-to-a-Teams-Meeting The September 13, 2026 research found individual spoken translation in Teams and Zoom, caption translation in Webex, and only one spoken-language pair per meeting in Google's standard Speech Translation. Those facts may have changed. Human interpreter audio channels are a separate service from AI interpretation. Recommend the simplest route that meets this meeting's needs and, if useful, one alternative. Show the evidence for the exact three-language experience, what is already available, and the remaining setup or entitlement. Do not treat a public product page as proof our tenant has it enabled. ### Configure the chosen route Once I choose a route, do available permitted setup yourself and give me only the clicks or account actions you cannot perform. Inspect the current settings before telling me to change them. If administrator action is required, prepare a concise request naming the feature, required license, meeting date, languages, and the evidence supporting the request; let me decide whether to send it. Prepare host instructions and a short participant note explaining how to select speaking and listening languages, how to hear the translation, and how to switch back to original audio. Prepare terminology from the agenda and source documents, with names, acronyms, amounts, dates, and product terms to test. Use a supported glossary if the chosen service offers one. Do not purchase, install an unapproved app, invite a bot to an actual meeting, or send participant messages without the relevant authorization. Keep preparation moving while such actions are pending. A drafted IT request is an access result, not a completed multilingual meeting. ### Rehearse every language direction Guide a short test with a speaker of each language using the actual accounts and devices. Prepare a realistic exchange: an introduction, a question, a reply, a number or deadline, a company term, and a proposed action. Rotate speakers so each person both speaks and receives the other two languages. Confirm translated AUDIO reaches every intended listener if speech was chosen. Test replies and language changes, not only one person's presentation. Check delay, overlap, echo, and whether original audio masks the translation. Ask listeners to repeat the meaning of an important sentence; use bilingual help where available. Do not claim to have heard or validated audio you cannot access. If a configuration fails, diagnose the actual setting or entitlement. Re-test after a material fix. Establish a practical fallback with me: translated captions, an approved external interpretation service, a human interpreter, or a different meeting format. Record which part of the original three-language goal that fallback does and does not meet. ### Run the meeting and close the loop Prepare a brief opening that tells everyone how translation works and invites them to flag unclear wording. Leave time for translated speech to finish between turns. During the meeting use the controls we tested; do not imply you are monitoring the live meeting unless you have an active working connection. At the end, help confirm key decisions, owners, and deadlines in the languages used, drawing on an accessible transcript or notes and flagging any ambiguous translation. Ask for brief feedback from each language group. Give me the tested settings, participant instructions, corrections, and whether everyone could contribute and understand. Mark the activity complete only after the real three-language meeting has happened; a successful rehearsal alone is preparation. These instructions were written in September 2026 using the frontier models available at the time. You may now have better tools or models, or restrictions that make some tasks harder. Your AI should adapt to the tools and access you actually have and find the best available way to help. Everything here is a starting suggestion for you and your AI, not a proven best practice for every setup. Feel free to rewrite any of it to better meet your needs.
Start with your usual meeting platform. These are useful routes to investigate, rather than a reason to buy a new tool before checking what you already have.
Set up the chosen route and give participants short joining instructions: where to select their languages, where the translated audio plays, and how to return to the original sound. Have the AI gather company names, acronyms, dates, and figures from the agenda for the test. If a license or administrator change is needed, let the AI prepare the precise request.
Rehearse with a speaker of each language on the devices they will actually use. Take turns asking and answering a real question. Test a number, a deadline, and a company term. Each participant should confirm that they understand the other two languages. Adjust the audio balance and leave room for the translation to finish. Agree on a fallback before the meeting if any direction does not work.
Run the meeting. Explain the translation setup at the start, invite people to flag unclear wording, and confirm decisions, owners, and deadlines before finishing. Afterwards, ask each language group whether they were able to contribute as fully as they wanted.
How it goes
What the AI will do
- Finds relevant meeting details and company tool guidance, then checks current translation options for your three languages.
- Prepares the setup, participant instructions, and a short three-language rehearsal.
What to have ready
- A meeting or project to start from, and the languages participants want to speak and hear.
- Access or brief account details when the AI cannot inspect your company's tools.
Where you come in
- Choose spoken translation or an agreed caption-based version, approve any needed setup, and join the rehearsal.
- Run the meeting and ask each language group whether they could understand and contribute.
What you'll get
A tested way to hold your meeting across three languages, with the actual outcome and any remaining limits made clear.
You're done when
You've held a real meeting in three languages and confirmed that participants could understand and respond. If you chose captions or another fallback, record that actual experience; a tool comparison or successful rehearsal alone is preparation.
View full AI instructions
Run a meeting in 3 languages at once.
Let people speak in the language in which they do their best thinking. Run a meeting where, for example, one colleague speaks English, another Spanish, and another French, while each hears the conversation in their preferred language. The right setup depends on your meeting platform, licenses, and the three languages you need.
Checked September 13, 2026: Teams Interpreter and Zoom Voice Translator provide spoken translation for supported languages. Webex's native real-time translation provides captions; Google Meet's standard speech translation currently supports one language pair per meeting. Wordly and KUDO offer additional spoken-translation routes. Features, access, and language coverage change quickly; use the prompt below to check your company's current options.
Step 1 — For the user
Choose a real conversation with participants who use three languages. Agree which language each person wants to speak and hear. Decide whether they need translated audio or whether reading translated captions would work for this meeting. The AI-help prompt below can find your current company options and guide the entire setup.
Step 2 — For the user
Start with your usual meeting platform. These are useful routes to investigate, rather than a reason to buy a new tool before checking what you already have.
Microsoft Teams: Interpreter
For supported languages and eligible participants, each person turns on Interpreter and chooses a listening language. Check the licenses and guest access for every person who needs it.
https://support.microsoft.com/en-us/teams/copilot/interpreter-in-microsoft-teams-meetings-and-calls
Zoom: Voice Translator
For supported languages, each participant chooses a speaking language and the language they want to hear. Check the Live Translation add-on or ZoomMate entitlement and the current desktop app requirements.
https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0084896
Webex or a wider language mix: Wordly / KUDO
Webex's native translation is captions. A service such as Wordly or KUDO can add translated audio, using an app, a meeting bot, or a separate listening page. Check the exact integration and three-language exchange before choosing it.
https://help.wordly.ai/what-is-meeting-bot
Google Meet: check the three-language requirement
Google's standard speech translation currently uses one pair of languages for the entire meeting. For this activity, investigate an approved add-on or agree to a different experience.
https://support.google.com/meet/answer/16221730?hl=en
Step 3 — For the user
Set up the chosen route and give participants short joining instructions: where to select their languages, where the translated audio plays, and how to return to the original sound. Have the AI gather company names, acronyms, dates, and figures from the agenda for the test. If a license or administrator change is needed, let the AI prepare the precise request.
Step 4 — For the user
Rehearse with a speaker of each language on the devices they will actually use. Take turns asking and answering a real question. Test a number, a deadline, and a company term. Each participant should confirm that they understand the other two languages. Adjust the audio balance and leave room for the translation to finish. Agree on a fallback before the meeting if any direction does not work.
Step 5 — For the user
Run the meeting. Explain the translation setup at the start, invite people to flag unclear wording, and confirm decisions, owners, and deadlines before finishing. Afterwards, ask each language group whether they were able to contribute as fully as they wanted.
Done when
You've held a real meeting in three languages and confirmed that participants could understand and respond. If you chose captions or another fallback, record that actual experience; a tool comparison or successful rehearsal alone is preparation.
Guidance for the AI
These are general instructions, not a description of this user's particular AI system, tools, access, or circumstances. Adapt the method to the user's goal and the capabilities you can actually use, while preserving the activity's essential sequence, review points, and intended result.
Start with the activity and the user's context
Read the complete activity and guide the user through it. Use the activity prompt yourself; the user does not need to paste it again. Keep the responsibilities of the user, the AI, and any colleague clear.
Begin with what the user has already supplied. Establish the intended result and resolve missing context through focused questions when needed. Work within the activity's stated scope, permissions, required confirmations, and stopping points, including any deliberate order for introducing information. Make progress with the available information and reasonable, clearly identified assumptions where the activity allows them.
Check the capabilities needed for this work
Inspect relevant available tools, connectors, and data. Use small, relevant, non-destructive checks to establish whether necessary access or a capability actually works. Naming a product does not establish access to it. Let this activity determine what needs checking; do not impose a universal preliminary questionnaire or a full system audit.
When useful access is missing:
- Explain what you cannot reach and how that material would help.
- Investigate practical setup, connection, export, or other access alternatives before asking the user to gather material or troubleshoot.
- If progress depends on access, request only the specific user action or permission needed to enable it or provide the material another way. Continue useful independent work while awaiting the response.
- Offer to walk the user through an export or upload. Welcome files, links, copied text, rough notes, or an interview as supported by your system and the activity, and use the best available route. If the missing access is optional, continue with what is available.
Ask focused questions and respect the answers
Ask questions only when necessary to complete the work well or satisfy the activity's required review points. Build on answers already supplied. Ask one question at a time, or a small group of closely related questions. Wait on work that depends on the answer, and continue useful work that does not. Explain unfamiliar language with examples where helpful.
Confirm answers or decisions you supply on the user's behalf before treating them as the user's final answers or decisions. This does not require separate approval of every sourced finding; follow the activity's specific review requirements.
Keep evidence and independent contributions distinct
Distinguish evidence, inference, and missing information. Check your work against the source material.
Use independent agents when your system actually supports delegation and independent investigation or review would improve the work:
- Give each agent a bounded brief and the context appropriate to its role.
- Keep discovery independent until synthesis where the activity requires it. Preserve any requirement for the user or colleagues to contribute before seeing other explanations.
- Follow the activity's stated fallback and any required confirmation when independent agents or fresh contexts are unavailable. Preserve reviewer isolation where required; describe shared-context or sequential passes accurately.
Produce, check, and revise the result
Do the substantive investigation and production. Carry the activity through to the most complete, usable result within its scope, rather than ending with a plan or handing the main work back to the user. When missing information does not prevent useful work, proceed with clearly identified assumptions where the activity permits them.
Check the result against the activity's completion criteria. At each substantive delivery, state what is complete and any material unfinished work, assumptions, helpful missing information, and remaining uncertainty. Explain how these affect what the user can use, and help the user revise the result.
Preserve the activity's stopping point. Do not turn a rehearsal, investigation, or test-design activity into execution that the user has not authorized.
Your AI prompt
Help me run a real meeting in three languages, using tools my company can actually use. Start with the meeting software and licenses we already have. Research current capabilities and guide setup and a short rehearsal before the real meeting.
Understand the meeting and find our existing setup
Use any meeting link, project name, or other context I have supplied. Inspect available calendar access for the meeting, attendee list, organizer, platform, and meeting type. Search relevant internal IT help pages, software catalogs, license records available to me, and support messages for translation features, approved meeting apps, and who can enable them. Search the related agenda, emails, chats, prior transcripts, and project documents for meeting purpose, terminology, names, and decisions people need to discuss. Explain which records you could actually access.
Use these records to establish the people and their roles. Do not infer their preferred language from nationality or surname. Confirm the three spoken/listening languages, who needs which, whether participants are external, and whether they are using computers, phones, or meeting-room devices. Ask one focused question at a time only for consequential missing information.
Clarify whether everyone needs translated speech in their ears, or whether translated captions would meet their needs. Treat three-language spoken interaction as the original target. If only captions or sequential two-language interpretation are available, explain that changed experience and wait for my choice.
Research today's workable routes
Browse current primary documentation and official integration listings. Date your findings. Check our platform first, then useful alternatives or approved add-ons. Investigate Microsoft Teams Interpreter, Zoom Voice Translator, Webex translation, Google Meet Speech Translation, and Wordly or KUDO only as relevant to our actual languages and setup.
Verify all of the following for each serious candidate:
- Actual spoken audio versus captions or translated transcripts.
- Three languages in the same meeting, including each person replying in their own language; a list of supported languages alone is not enough.
- Host and attendee license requirements, guest access, device support, administrator controls, and any regional or account rollout limits.
- Native feature, installable app, additional browser page, bot participant, or custom integration; where each person hears the output.
- Current setup instructions, known delay or language-switching behavior, and price or usage allowance when publicly established. Distinguish a quoted enterprise price from public list pricing and leave unknown charges unknown.
Starting references, to recheck rather than assume current:
- Teams: https://support.microsoft.com/en-us/teams/copilot/interpreter-in-microsoft-teams-meetings-and-calls
- Zoom: https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0084896
- Webex: https://help.webex.com/en-us/article/7dzhht/Real-Time-Translation-in-Webex-Meetings-and-Events
- Meet: https://support.google.com/meet/answer/16221730?hl=en
- Wordly: https://help.wordly.ai/what-is-meeting-bot
- KUDO: https://support.kudoway.com/hc/en-us/articles/40489091825047-Adding-KUDO-app-to-a-Teams-Meeting
The September 13, 2026 research found individual spoken translation in Teams and Zoom, caption translation in Webex, and only one spoken-language pair per meeting in Google's standard Speech Translation. Those facts may have changed. Human interpreter audio channels are a separate service from AI interpretation.
Recommend the simplest route that meets this meeting's needs and, if useful, one alternative. Show the evidence for the exact three-language experience, what is already available, and the remaining setup or entitlement. Do not treat a public product page as proof our tenant has it enabled.
Configure the chosen route
Once I choose a route, do available permitted setup yourself and give me only the clicks or account actions you cannot perform. Inspect the current settings before telling me to change them. If administrator action is required, prepare a concise request naming the feature, required license, meeting date, languages, and the evidence supporting the request; let me decide whether to send it.
Prepare host instructions and a short participant note explaining how to select speaking and listening languages, how to hear the translation, and how to switch back to original audio. Prepare terminology from the agenda and source documents, with names, acronyms, amounts, dates, and product terms to test. Use a supported glossary if the chosen service offers one.
Do not purchase, install an unapproved app, invite a bot to an actual meeting, or send participant messages without the relevant authorization. Keep preparation moving while such actions are pending. A drafted IT request is an access result, not a completed multilingual meeting.
Rehearse every language direction
Guide a short test with a speaker of each language using the actual accounts and devices. Prepare a realistic exchange: an introduction, a question, a reply, a number or deadline, a company term, and a proposed action. Rotate speakers so each person both speaks and receives the other two languages.
Confirm translated AUDIO reaches every intended listener if speech was chosen. Test replies and language changes, not only one person's presentation. Check delay, overlap, echo, and whether original audio masks the translation. Ask listeners to repeat the meaning of an important sentence; use bilingual help where available. Do not claim to have heard or validated audio you cannot access.
If a configuration fails, diagnose the actual setting or entitlement. Re-test after a material fix. Establish a practical fallback with me: translated captions, an approved external interpretation service, a human interpreter, or a different meeting format. Record which part of the original three-language goal that fallback does and does not meet.
Run the meeting and close the loop
Prepare a brief opening that tells everyone how translation works and invites them to flag unclear wording. Leave time for translated speech to finish between turns. During the meeting use the controls we tested; do not imply you are monitoring the live meeting unless you have an active working connection.
At the end, help confirm key decisions, owners, and deadlines in the languages used, drawing on an accessible transcript or notes and flagging any ambiguous translation. Ask for brief feedback from each language group. Give me the tested settings, participant instructions, corrections, and whether everyone could contribute and understand. Mark the activity complete only after the real three-language meeting has happened; a successful rehearsal alone is preparation.
These instructions were written in September 2026 using the frontier models available at the time. You may now have better tools or models, or restrictions that make some tasks harder. Your AI should adapt to the tools and access you actually have and find the best available way to help. Everything here is a starting suggestion for you and your AI, not a proven best practice for every setup. Feel free to rewrite any of it to better meet your needs.
These instructions were written in September 2026 using the frontier models available at the time. You may now have better tools or models, or restrictions that make some tasks harder. Your AI should adapt to the tools and access you actually have and find the best available way to help. Everything here is a starting suggestion for you and your AI, not a proven best practice for every setup. Feel free to rewrite any of it to better meet your needs.