AI Dubbing & Captions

A new language.
The same curiosity.

Hear web audio in all 78 Gemini Live Translation languages. Follow along with bilingual captions, and keep the original sound within reach.

Available for desktop Chrome. The Edge Add-ons listing is coming soon.
A Gemini API key is required. Google API fees may apply.

World Science Keynote · Speech Neuroscience
Live translation
Global Keynote 2026 Streaming video
"Sound carries emotion, while words structure understanding." "Âm thanh truyền tải cảm xúc, còn ngôn từ xây dựng sự thấu hiểu."
Audivoya
Ready
Listen in
Tiếng Việt (Vietnamese)▾
Original audio
25%
Dubbed voice
85%
Start dubbing →
Made for everyday listening Learn something new Follow a conversation Explore another perspective

Make the audio
work for you.

Choose how you listen, read and stay in control.

Hear it in your language.

Translate selected-tab audio into any of the 78 documented Gemini Live Translation languages through your Gemini API account.

English → Tiếng Việt Español +75

Keep both sides of the story.

View original and translated captions. Export VTT when you want a copy; timestamps follow caption arrival.

Follow the original speech in real time.
Đồng thời theo dõi phụ đề bản dịch trực tiếp.

Find your listening balance.

Adjust each volume, follow the main player's speed, pick how long a session may run, or use Audio monitor to listen locally without AI uploads.

Original
25%
Dubbed
85%

78 languages.
One listening experience.

Choose any language documented for Gemini Live Translation, including Chinese Simplified and Traditional, and Portuguese for Brazil and Portugal.

See all 78 supported languages
  • Afrikaans
  • Akan
  • Albanian
  • Amharic
  • Arabic
  • Armenian
  • Azerbaijani
  • Basque
  • Belarusian
  • Bengali
  • Bulgarian
  • Burmese (Myanmar)
  • Catalan
  • Chinese (Simplified)
  • Chinese (Traditional)
  • Croatian
  • Czech
  • Danish
  • Dutch
  • English
  • Estonian
  • Filipino
  • Finnish
  • French
  • Galician
  • Georgian
  • German
  • Greek
  • Gujarati
  • Hausa
  • Hebrew
  • Hindi
  • Hungarian
  • Icelandic
  • Indonesian
  • Italian
  • Japanese
  • Javanese
  • Kannada
  • Kazakh
  • Khmer
  • Kinyarwanda
  • Korean
  • Lao
  • Latvian
  • Lithuanian
  • Macedonian
  • Malay
  • Malayalam
  • Marathi
  • Mongolian
  • Nepali
  • Norwegian
  • Persian
  • Polish
  • Portuguese (Brazil)
  • Portuguese (Portugal)
  • Punjabi
  • Romanian
  • Russian
  • Serbian
  • Sindhi
  • Sinhala
  • Slovak
  • Slovenian
  • Spanish
  • Sundanese
  • Swahili
  • Swedish
  • Tamil
  • Telugu
  • Thai
  • Turkish
  • Ukrainian
  • Urdu
  • Uzbek
  • Vietnamese
  • Zulu

Based on Google’s Live Translation language list, checked October 3, 2026. Availability follows the supported model; quality varies by language and source. This is provider-documented support, not a listening benchmark in every language.

Your tab.
Your language.
Your call.

Start a session when you choose. Move between videos on the same website while the control panel is closed.

Open the illustrated guide
  1. 1

    Open the media you want to understand.

    Use a supported website in desktop Chrome or Edge, with media you have permission to process.

  2. 2

    Choose a language and connect Gemini.

    Enter your key in the extension. Review Google's audio-sharing notice, fees and account terms.

  3. 3

    Press Start. Adjust as you listen.

    Choose Start dubbing, or Start with sync window for a delayed picture. Control volumes and captions. Stop anytime from the panel or with Alt + Shift + S.

Actual Audivoya sync window showing a locally buffered picture of a generated demo clip above a collapsed Controls panel
Actual sync window · owned generated demo clip
Adjustable picture delay

A little delay.
A better chance to align.

Start with sync window opens an experimental viewer that buffers the picture on your device while translation continues. Adjust the delay to improve the viewing experience.

It adds a viewing delay; it does not speed up AI inference. Translation timing and accuracy vary, and exact word alignment is not guaranteed.

Learn about synchronized viewing

Know what leaves
your browser.

Dubbing sends selected-tab audio directly to Google. Your provider account determines its fees and data-use terms.

Read the privacy policy

Audio goes directly to the provider.

No developer-operated audio server. Google processes dubbing requests under its own terms.

Enter your key once, in the extension.

The latest candidate encrypts it in this browser profile and restores it automatically. No extra app, password or cloud sync. Forget key removes the saved record.

You decide when capture starts and stops.

No automatic audio capture. No developer analytics or advertising. Optional sync pictures stay on your device.

Before you press play.

Common questions about requirements, delay, and usage.

Can I install it from the stores today?

Yes. Audivoya is available in the Chrome Web Store for desktop Chrome. The Edge Add-ons listing is still coming soon.

Do I need a Gemini API key?

Yes, for dubbing. The extension uses your Gemini API account. Google API charges, quotas, regional access and data-use terms apply. Audio monitor works locally without a provider key.

See the key setup guide

Does it translate instantly?

No. Translation needs processing time and enough speech context. Delay depends on your connection, content, model and playback speed. The optional sync window delays the picture to improve presentation alignment.

Which browsers and languages are supported?

The current release is available for desktop Chrome. The Edge Add-ons listing is being prepared. All 78 languages documented for Gemini Live Translation are supported by the Chrome release. See the full language list. Live dubbing on Firefox, Safari and mobile is not available. Website and protected-media compatibility varies.

Will it keep up with faster video?

Dubbed audio follows the main observable HTML player within 0.25×–4×. Some embedded or custom players do not expose their speed. Faster playback does not accelerate Gemini inference and can reduce translation quality.

Can I leave it running for hours?

Yes. Under Audio & settings, Stop automatically after offers 5, 15, 30 and 60 minutes, 2, 3, 4 and 8 hours, or Never. The default is 60 minutes. With Never, capture and audio sent to Google continue, and Google API fees may accrue, until you press Stop, close the tab or leave the website.

Bring a new language
to your browser.

Install the Chrome release today. The Edge listing is coming soon.