How to use simultaneous interpretation on Google Meet! A complete guide covering Japanese language support, setup, and situations where human interpretation is needed.
There are three main ways to perform simultaneous interpretation on Google Meet: "voice translation," "translated subtitles," and "human interpretation."
With voice translation, AI can convert what you say into speech in another language.
On the other hand, as of September 25, 2026, it does not support Japanese, and there are limitations on the time and situations in which it can be used.
For conversations that include Japanese, you can use translated subtitles to display the translated text on the screen.
However, in important business negotiations or international events, where handling specialized terminology and accurately conveying nuances are required, it may be more appropriate to arrange for a human interpreter.
This article explains how to use simultaneous interpretation in Google Meet, including setup instructions and situations where human interpretation may be necessary.
Three methods for simultaneous interpretation on Google Meet
There are three main ways to interact with participants who speak different languages using Google Meet:
method | Delivery method | Japanese | Points to note | Suitable cases |
Voice translation | AI-translated audio | Currently not available to the general public. | There are restrictions on supported languages, usage time, and recording/live streaming. | Online meetings between languages that support each other |
Translated subtitles | Text translated by AI | correspondence | There are conditions regarding the editions of Google Workspace that can be used. | A meeting where you can confirm the Japanese text. |
Simultaneous interpretation by human interpreters | Audio of interpretation by an interpreter | Depending on the interpreter's languages | A system is needed to deliver the original audio and the translated audio separately. | International events and venues that prioritize accurate information dissemination |
Now, let's take a closer look at each method.
Voice translation
Voice translation is a feature where AI recognizes what participants say and converts it into speech in another language for delivery.
This method is convenient when you want to proceed with the conversation by audio, as you don't need to keep reading subtitles.
According to Google's Google Meet Help page, "About Voice Translation" (as of September 25, 2026), the translated audio is played back in a voice similar to the original speaker's, and the translation takes a few seconds.
However, at this time, it is not possible to use it to "listen to what you say in English in Japanese audio."
For meetings where Japanese is required, translated subtitles or human interpretation will be necessary.
Furthermore, in Gemini 3.5 Live Translate , which Google announced on its official blog on June 9, 2026 , plans to expand Google Meet's voice translation to more than 70 languages and more than 2,000 language combinations.
In addition to checking whether Japanese is included, please refer to the official information released after the official general availability date for details such as the eligible editions and release dates.
Translated subtitles
Translation subtitles are a feature where AI recognizes what is said during a meeting and displays the translated text on the screen.
Unlike voice translation, Japanese can be used as both the source and target languages.
Therefore, if you want to check the content of a meeting conducted in English in Japanese, translated subtitles are very useful.
However, translated subtitles require you to read the text displayed on the screen.
When attending an event while watching videos or presentation materials, it can sometimes be burdensome to simultaneously follow along with the subtitles.
It's also important to note that the transcription and translation results can vary depending on factors such as the speaker's speaking speed and clarity, overlapping statements from multiple speakers, and the use of technical terms and proper nouns.
Simultaneous interpretation by human interpreters
In simultaneous interpretation by two interpreters, the interpreter listens to what the speaker or participant is saying and translates it into another language with a slight delay.
Unlike AI translation, it is more likely to translate while taking into account the context of the conversation, specialized terminology, and subtle nuances of language, making it suitable for important business negotiations, international conferences, and overseas events.
However, simply having an interpreter participate in a Google Meet meeting does not automatically create a simultaneous interpretation environment.
If the original speaker's audio and the interpreter's translation are played simultaneously in the same meeting, the two audio tracks may overlap, potentially making it difficult for participants to understand.
Therefore, it is important to separate the audio paths so that the original audio is sent to the interpreter and the interpreter's translation is delivered to the participants who need it.
For example, there are the following methods:
Prepare a separate online meeting for interpretation.
Using a remote simultaneous interpretation system
Use an audio mixer to split the distribution to different destinations.
For events that combine a physical venue with Google Meet, it's necessary to design the audio flow separately for each stage, such as "audio played at the venue," "audio delivered to online participants," "original audio heard by interpreters," and "translated audio delivered from interpreters to participants."
For corporate events and international conferences, it's crucial to prepare not only for interpreter arrangements, but also for audio and streaming systems.
Requirements for using Google Meet's simultaneous interpretation (voice translation) function
Google Meet's voice translation feature is not available for all accounts or languages.
If you plan to use it for an event or meeting, you should check the terms of use in advance.
The main conditions are as follows:
The language you use must support voice translation.
The account you are using must be eligible for the feature.
Participants must allow voice translation.
Now, let's take a closer look at each of these conditions.
The language you use must support voice translation.
To use Google Meet's voice translation feature, the language you are speaking and the language you are translating to must be compatible.
According to Google's Google Meet Help page, "About Voice Translation ," as of September 2026, voice translation will be generally available between English and the following six languages.
French
German
Hindi
Italian
Portuguese
Spanish
For example, translation from English to Spanish and from Spanish to English is possible.
On the other hand, it does not support combinations that do not include English, such as French to German.
Furthermore, Japanese is not currently included in the general release.
Therefore, it is not possible to translate Japanese speech into English audio, or to listen to English speech in Japanese audio.
To determine if it will be available at the time of your event, check both the official Google Meet help page and the actual settings screen.
The account you are using must be eligible for the feature.
Voice translation is not a feature available for all Google accounts.
According to the official Google Meet Help page, " About Voice Translation " (as of September 25, 2026), the following plans and editions are eligible for voice translation:
Google AI Pro
Google AI Ultra
Google Workspace Business Standard, Business Plus
Google Workspace Enterprise Standard, Enterprise Plus
Google Workspace Frontline Plus
Google AI Pro for Education
Google AI Expanded Access
Even if you are using an eligible plan, you cannot use voice translation if your organization's Google Workspace administrator has disabled it.
Therefore, if you plan to use it for an event, make sure that the voice translation option is displayed on the account that will actually be hosting the event.
Organizations participating in the alpha version of the voice translation program may find that the screen layout and operation methods differ from the general release version, so it's a good idea to conduct a test meeting before going live.
Participants must allow voice translation.
Even if the host enables the voice translation feature for the entire meeting, not all participants' comments will be automatically translated.
Participants also need to set their preferred language to speak and hear, and allow their voice to be translated.
According to Google Meet's official help documentation, if a participant has not agreed to have their voice translated, they may not be able to hear the translated audio.
Troubleshooting voice translation
If you cannot hear the participant's translation or if the voice translation is not working as expected, the following reasons may apply:
The participant has not agreed to have their voice translated during the meeting.
Source: Google Meet Help " About voice translation "
Therefore, when sending out event invitations, don't just share the meeting URL; also explain how to open the voice translation badge, how to change language settings, and how to allow translation.
Especially in events with many external participants, setting the schedule just before the start may cause delays.
It is important to set aside time in advance to check the connection and ensure that participants can hear the translated audio correctly.
Main limitations of Google Meet's simultaneous interpretation (voice translation function)
Google Meet's voice translation feature may not be available even if the requirements are met, depending on the length of the event, the number of languages required, and whether or not it is being recorded or streamed.
The main restrictions are as follows:
Up to 90 minutes per meeting
Only one language combination can be used per meeting.
Not available for recorded or live streaming.
Now, let's take a closer look at each of these restrictions.
Up to 90 minutes per meeting
According to Google Meet's official help documentation (as of September 25, 2026), voice translation is limited to 90 minutes per meeting.
The time limit for audio translation per meeting is 90 minutes.
Source: Google Meet Help " About voice translation "
Therefore, for events exceeding 90 minutes, including lectures and Q&A sessions, it is not possible to use voice translation continuously from beginning to end.
Especially in international conferences and long online events, the inability to use voice translation midway through can significantly impact participants' understanding.
If the interpretation time exceeds 90 minutes, you should decide on a method that suits the overall duration of the event, such as arranging for a human interpreter or using a different system that can handle longer interpretation sessions.
Only one language combination can be used per meeting.
Currently, Google Meet's voice translation feature, which is generally available to the public, only allows one language combination to be used per meeting.
For example, in a meeting where English and Spanish are set up, you cannot simultaneously play audio translations in English and French.
While it is possible to switch to a different language in the middle of a meeting, you will need to stop voice translation, set the new language combination, and then re-enable it.
Also, any changes you make will be reflected for all participants.
Therefore, it is not suitable for events where you want to deliver audio translations simultaneously to participants speaking multiple languages, such as English, French, and Spanish.
When simultaneous interpretation into multiple languages is required, it is appropriate to provide separate interpreters and audio channels for each language.
Not available for recorded or live streaming.
Google Meet's official help page states that voice translation is not available for recordings or live streams.
If you want to include interpreted audio in the archived video to be released after the event, or if you want to live stream in multiple languages to people other than meeting participants, please note that Google Meet's voice translation alone may not be sufficient.
For events like these, it's necessary to have an audio design that includes distribution and recording, such as a system that allows for separate recording and distribution of the original audio and the interpreter's voice.
How to set up voice translation and translated subtitles for simultaneous interpretation in Google Meet
If you want to hear translated audio in Google Meet, set up voice translation using a combination of supported languages.
On the other hand, if you need a language that is not currently supported by the voice translation system, such as Japanese, you can use translated subtitles.
The process from setup to pre-launch checks is as follows:
Enable voice translation in meetings
Participants can set the language they will speak and the language they will listen to.
If you need Japanese, set up translated subtitles.
Check with actual speech before the real thing.
From here, let's take a closer look at the desktop version of the instructions provided in Google's official help documentation.
1. Enable voice translation in meetings.
First, join the Google Meet meeting using an account that supports voice translation, and enable voice translation for the entire meeting.
The setup process is as follows:
Open [Meeting Tools] in the lower right corner of the meeting screen.
Select [Voice Translation]
Choose the language combination you want to use.
Select [Enable translation for all participants]
When voice translation is enabled, a voice translation badge will appear on participants' screens.
If the [Voice Translation] option itself does not appear, check not only the language you are using, but also your host's contract plan and administrator settings.
It's important to verify beforehand that you can operate the system using the actual account you'll be using, rather than setting it up for the first time during the event.
2. Set the languages that participants will speak and listen to.
Once voice translation is enabled for the entire meeting, each participant will set their preferred language.
The basic process is as follows:
Open the voice translation badge at the top of the screen.
Choose your speaking language.
Choose the language you want to hear.
If you haven't updated your [Speaking Language] settings, select [Allow Translation].
Click [Translate] to allow your voice to be translated.
The languages you can choose from are limited to the language combination set for the entire meeting.
Additionally, if participants have not completed the necessary settings or granted the required permissions, their comments may not be translated correctly.
For events with many external participants, it's helpful to provide instructions on how to change the language settings in advance, in addition to the meeting URL.
3. If Japanese is needed, set up translated subtitles.
As of September 25, 2026, Japanese is not included in the generally available voice translation services.
Therefore, if you want to check English statements in Japanese, you should use translated subtitles.
The basic setup procedure for the PC version is as follows:
Open [Other Options] during a meeting
Select [Subtitles] from [Settings].
Under [Language used in the meeting], select the language that will actually be spoken.
Turn on [Subtitle Translation]
Choose the language you want to translate into.
Since the target language can be set for each participant, even within the same meeting, some people can view subtitles in Japanese while others view them in a different language.
However, translated subtitles are merely a function to check the content in text.
For events where it's difficult to follow along with subtitles while viewing presentation materials and videos, or when a direct Japanese audio translation is necessary, alternative methods such as using a human interpreter should be considered.
4. Practice speaking before the actual performance.
It's important not only to enable voice translation and translated subtitles in the settings screen, but also to verify that they translate correctly in the same environment as the production environment.
During the rehearsal, use the actual computers, microphones, and network that will be used, and have the speakers deliver content that is as close to the actual presentation as possible.
In particular, you need to check whether the following content is recognized and translated as intended.
Company Name
Product name
person name
Technical terms
numbers
We also check whether the speaking speed is too fast, whether multiple people are speaking at the same time, and whether any delays in translation will affect the progress of the event.
It's not enough for it to simply be working correctly on the organizer's screen.
Make sure that translated audio and subtitles are being received correctly, even in environments where participants have set different languages.
For external events, it's reassuring to have alternative procedures in place in case the translation function becomes unavailable. These include switching to translated subtitles, providing instructions via chat, or switching to a human interpreter.
There are cases where Google Meet's translation function alone is insufficient.
Google Meet's voice translation and translated subtitles are very convenient.
However, depending on the content of the event and the delivery method, the standard features may not be sufficient to provide the necessary interpretation environment.
The main cases where Google Meet's translation function alone is insufficient are as follows:
I want to deliver Japanese in real-time audio.
I want to deliver the translated audio to multiple languages simultaneously.
We want to deliver translated audio to live streams and recordings as well.
I want to prioritize accuracy and context.
Now, let's take a closer look at each case.
I want to deliver Japanese in real-time audio.
While Google Meet's translation function can display Japanese subtitles, it cannot deliver Japanese audio interpretation to participants using its voice translation function.
Therefore, for events where you want participants to hear the speeches of speakers from overseas in Japanese audio, you need to arrange for a human interpreter and prepare a separate audio channel to deliver the interpreted audio to the participants.
For example, one approach is to provide an audio environment for interpreters, or to create a system that allows participants to choose between the original audio and a Japanese interpreted audio.
Before deciding on the streaming configuration, make sure that Google Meet supports voice translation in the required languages at the time of the event.
I want to deliver the audio translation to multiple languages simultaneously.
For events where an English lecture needs to be simultaneously interpreted into multiple languages such as Japanese, Chinese, and French, Google Meet's translation function alone may not be sufficient.
For these multilingual events, it's necessary to assign interpreters for each language, provide an environment where each interpreter can hear the original audio, and offer audio channels where participants can choose and listen to their preferred language.
Confirm the required number of languages, the number of participants, and whether or not there will be a Q&A session, and then plan the configuration by combining remote simultaneous interpretation systems and language-specific distribution environments.
We want to deliver translated audio to live streams and recordings as well.
If you want to deliver the interpreted audio not only to those participating in Google Meet, but also to viewers of the live stream and those who will watch the recording later, you need to design the system to include the distribution and recording methods.
For example, you could live stream the original audio version and the interpreted audio version separately, or provide separate viewing options for each language.
Regarding recording, one possible method is to record the original audio and the interpreted audio separately and then edit them into separate videos for each language.
After deciding how the video will be released following the event, confirm in advance whether subtitles alone will suffice or if interpreted audio is also necessary.
I want to prioritize accuracy and context.
While AI-powered real-time translation is convenient, it doesn't always accurately translate technical terms, proper nouns, or speaker-specific expressions.
In particular, for events where it is important to accurately convey even the subtle nuances of statements like the following, employing a human interpreter is a suitable approach.
International conference
Product Announcement
Explanation of Management Policy
As an interpreter, you can review the presentation materials and technical terms in advance and interpret based on the content and flow of the event.
For high-priority events, one approach is to primarily use human interpreters while supplementing them with Google Meet's translated subtitles.
At LIFE.14, we have a proven track record of working on various events that require simultaneous interpretation.
If you have any concerns about setting up an audio and streaming environment, including interpreters, please contact LIFE.14.
Google Meet's translation function has its limitations! For events requiring interpretation, let a professional handle everything, including technical support.
Google Meet's voice translation and translated subtitles can be used for multilingual online meetings, provided the supported languages and usage conditions are met.
On the other hand, if you want to deliver Japanese audio interpretation, provide simultaneous interpretation in multiple languages, or even live stream and record the session, Google Meet's standard features may not be sufficient.
Especially for events involving interpreters, it's necessary to design the audio and streaming environment, including how to differentiate between the original audio heard by the interpreter and the translated audio delivered to the participants.
As explained on our official service page , LIFE.14 provides comprehensive support for business events, including audio and video, online streaming, and photography.
Even for events with interpreters, you can consult with us about all the necessary technical support, including audio path setup, equipment installation, streaming operation, video switching, and recording.
If you would like to request comprehensive technical support for an event with interpreters, please contact LIFE.14.
# google meet simultaneous interpretation
![[Photography and video production] EU-Japan Centre for Industrial Cooperation "55th WCM Program"](https://static.wixstatic.com/media/a17cef_25b5f3045e9b455bb15e20b677bd5fbc~mv2.jpeg/v1/fill/w_1000,h_1000,fp_0.50_0.50,q_30,blur_30,enc_avif,quality_auto/a17cef_25b5f3045e9b455bb15e20b677bd5fbc~mv2.jpeg)
![[Photography and video production] EU-Japan Centre for Industrial Cooperation "55th WCM Program"](https://static.wixstatic.com/media/a17cef_25b5f3045e9b455bb15e20b677bd5fbc~mv2.jpeg/v1/fill/w_1168,h_1168,fp_0.50_0.50,q_90,enc_avif,quality_auto/a17cef_25b5f3045e9b455bb15e20b677bd5fbc~mv2.jpeg)
Comments