How to Live Speech Translate WhatsApp on the Web?
You're on a WhatsApp call with someone who speaks a language you can almost follow, but not at full speed. You don't want to ask them to slow down, repeat themselves, or set up a clunky three-way interpreter. You just want a private, realtime voice translator that runs on your side of the screen and turns what they say into the language you understand best.
Now that WhatsApp Web does voice and video calls right in the browser, that's finally easy. You point Whisperr at your WhatsApp call tab and you've got a free personal interpreter, one nobody else on the call can see, that you control entirely, pointed at any language pair you like.
This guide walks through the one reliable way to do it, end to end.
Why WhatsApp doesn't hand you a live translator
WhatsApp has no built-in translation for calls. There's no toggle that says "translate only the other person, only into my language, only on my screen." Calls are end-to-end encrypted and that's it, so what you hear is what you get.
The workaround is to treat the call audio like any other audio source and pipe it into a translation layer running alongside the call. Whisperr is built exactly for that. It captures whatever audio is playing in a browser tab and gives you live voice translate captions, plus spoken voice translation, in 100+ language pairs. The catch used to be that WhatsApp calls only lived on your phone or the desktop app, where a browser can't reach the audio. As of early 2026, WhatsApp Web added native voice and video calling in the browser, which is exactly the door this method needs.
This is the same browser-tab capture pattern that works for Zoom, Microsoft Teams, Google Meet, and Twitch. WhatsApp Web is just one more audio source it works with.
What you need before you start
- A Whisperr account. The free tier is enough for short calls.
- A laptop or desktop with any modern browser (Chrome, Edge, Firefox, Safari, Brave, Arc, or anything Chromium-based). Any browser that supports tab-audio capture works.
- WhatsApp Web set up. Open web.whatsapp.com and link it to your phone by scanning the QR code. Make sure the call buttons appear in your chats. Browser calling rolled out through 2026, so update your app if you don't see them yet.
The one way that works: capture WhatsApp Web in a browser tab
This is the cleanest setup. You make or answer the WhatsApp call in a browser tab and let Whisperr capture the tab audio directly. No microphone, no speaker, no second device. The audio goes from WhatsApp's web player straight into Whisperr, before it ever reaches your ears, so it works with headphones or AirPods too, because the capture happens digitally.
Step 1: Open your WhatsApp call in a browser tab
Go to web.whatsapp.com in a browser tab and sign in by scanning the QR code with your phone. Open the chat with the person you're calling and start the call, or answer their incoming call, using the voice or video call button right there in the browser. This is the one non-obvious detail of the whole setup. Whisperr captures audio from a browser tab, so the call has to be playing in a tab, not the phone app or the standalone WhatsApp desktop app. Any modern browser works here.
Step 2: Open the Whisperr web app in a second tab
In a new tab, open the Whisperr web app and sign in. Don't close the WhatsApp tab. Whisperr needs it open and playing to capture the audio.
Step 3: Pick the two languages
Use the two language dropdowns at the top of the Whisperr interface and pick the two languages on the call, for example English and Japanese. You don't have to set a source and a target. Whisperr does two-way translation by default, so it handles voice translation in both directions and the order doesn't matter. If you only want one direction, see the next step.
Step 4: Keep it two-way, or set one direction
By default Whisperr translates both ways, which is fine for most calls. If you'd rather keep it clean and only read the other person, tap the arrow button between the two language selectors to switch to one direction. That way it only translates one way, from the other person's language into yours, and you won't see the other translations you don't want to see. For an accurate Japanese translator feed on an english to japanese translation voice call, this gives you a single, tidy stream that reads like a private interpreter.
Step 5: Enable Live Speech
To hear the translation spoken aloud, turn on "Auto-speak translations." It speaks each translation as it's confirmed, so use headphones to keep it from bleeding back into the call. If you like, set the Speaking speed slider to whatever suits your ears.
Step 6: Start a New Recording and choose Screen Capture
Click New Recording, then click the recording icon and choose Screen Capture. A picker pops up.
Step 7: Pick the WhatsApp tab and share its audio
In the picker, choose Tabs, select your WhatsApp Web call tab, make sure Share tab audio is ticked, and click Share. Whisperr immediately starts capturing the call audio. If you forget to tick "Share tab audio," Whisperr gets video frames but no sound, so there's nothing to translate. This is the single most common mistake on this flow, so double-check the box before you hit Share.
Step 8: Split screen for readability
You can also split the WhatsApp tab alongside Whisperr by right-clicking the tab and choosing "New Split View with Current Tab." That lets you watch the call and read the live translations side by side, without flipping between tabs.
Step 9: Listen and read along
That's it. The other person speaks normally, the live voice translation comes out of your speakers or headphones, and the translated captions stream onto your screen in your language. Nobody else on the call sees anything. Whisperr runs entirely on your side.
Why this beats the alternatives
It's genuinely free for short calls. The Whisperr free tier covers quick conversations, so you're not paying for a per-seat interpreter just to understand one person.
It's private. Whisperr runs in a separate tab on your machine. The other person doesn't install anything, change any settings, or even know it's there.
You decide the direction. Two-way translation is on by default, or you can switch to one direction so you only read the other person in your language, with no extra clutter.
It works without a loud speaker. Tab capture grabs the audio digitally, so you can wear headphones or AirPods. Useful late at night, in a shared space, or an open office.
It's platform-agnostic. The same tab-capture flow works on Zoom, Google Meet, Microsoft Teams, Webex, YouTube, and Discord. One workflow, every platform.
100+ language pairs, including the long tail most consumer tools under-serve. English to Japanese translation voice, Korean to English, Spanish to English, Russian to English, Mandarin, Vietnamese, Portuguese, Polish, Thai, and the rest.
Frequently Asked Questions
Does WhatsApp have a built-in translator just for me?
No. WhatsApp calls have no translation feature at all. Running Whisperr alongside the call in a browser tab is what gives you a personal interpreter on the free tier, just for you.
Will the other person know I'm using it?
No. Whisperr runs in a separate browser tab on your screen, not inside the WhatsApp call. Nothing appears on their end.
Do I have to use WhatsApp Web, or can I use my phone or the desktop app?
For this tab-capture method, use WhatsApp Web in a browser. Tab capture only reaches audio that's playing in a browser tab, which the phone app and standalone desktop app aren't. WhatsApp Web added native browser calling in 2026, which is what makes this possible.
Can I read only the other person and not my own speech?
Yes. Whisperr is two-way by default, but you can tap the arrow button to set one direction. Then it only translates the other person into your language, and you won't see the translations you don't want.
Do I need a loud speaker for this?
No. Tab capture pulls the audio digitally before it reaches your output device, so headphones and AirPods work fine.
Does it work for WhatsApp video calls too?
Yes. As long as the call is running in your WhatsApp Web tab, Whisperr captures the audio the same way, voice or video.
Try it on your next WhatsApp call
The whole flow, top to bottom:
- Open web.whatsapp.com in a browser tab and start or answer the call there.
- Open the Whisperr web app in a second tab and sign in.
- Pick the two languages, for example English and Japanese. Two-way is on by default, or tap the arrow for one direction.
- Turn on Auto-speak translations, and set the speaking speed if you like.
- New Recording, then Screen Capture, then Tabs, pick the WhatsApp tab (with Share tab audio ticked), and click Share.
- Read along. Your own realtime voice translator, just for you.
Start a free session at the Whisperr web app.