Audivoya - AI Dubbing & Captions

Listen to website audio in any of the 78 output languages documented for Gemini Live Translation with Audivoya. Translate the tab you choose into spoken audio and bilingual captions, while keeping control of your listening experience. WHAT YOU CAN DO • Listen to translated speech in all 78 documented Gemini Live Translation languages, including English, Vietnamese, Spanish, Japanese, Korean, French, German and Arabic. • Read original and translated captions, show captions on the website, and export them as a VTT file. • Adjust original audio and translated speech volumes separately. • Follow the main HTML player's playback speed, within 0.25×–4×. • Choose an automatic stop time and stop capture with Alt+Shift+S. • Use Audio monitor to listen locally without sending audio to an AI provider. SUPPORTED OUTPUT 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. Language availability follows the supported translation model. Translation quality varies by language, source speech and playback conditions; this list describes provider-documented support, not a listening benchmark for every language. OPTIONAL SYNCHRONIZED VIEWING The experimental sync window buffers the selected tab's picture locally while translation continues. Adjust the viewing delay to improve alignment with translated speech. Expand Controls in the sync viewer to play/pause, skip ten seconds, change playback speed, adjust volumes or mute. Commands act on the source player; seeking refills the delayed view. Use the source tab if a player is unavailable. This adds a viewing delay; it does not make AI translation instantaneous. Buffered images stay on your device. GET STARTED 1. Open a website tab with the audio or video you want to translate. 2. Open Audivoya and choose the language you want to hear. 3. Enter your Gemini API key, read the audio-sharing notice, and click Start dubbing. 4. Allow access to the Google API when your browser asks for permission. A Gemini API key with access to the supported live translation model is required for dubbing. Audivoya does not include Google API credits. Provider charges, quotas, account eligibility and regional availability depend on your Google account. SYNC VIEW CONTROLS Adjust original and dubbed audio volumes or mute output directly in the sync viewer. Temporary translation reconnects preserve the original audio and delayed picture. When a session ends, its viewer closes. Controls start collapsed to leave more room for the picture. Playback controls support observable top-frame HTML media; custom and embedded players may require the source tab. Fullscreen toggles to Exit fullscreen when active and follows browser fullscreen changes, including F11. Leaving fullscreen restores the previous normal or maximized window mode. During playback changes or audio bursts, Audivoya may resynchronize its bounded translation buffer without ending the session. Some translated speech may be skipped; a notice explains this. Frequent seeks may temporarily delay translation setup while original playback and the sync viewer remain available. PRIVACY AND CONTROL Continue on the same website by default: while a session is active, links, video changes and reloads in the selected tab retain capture on the same origin (scheme, hostname and port). No other tab or website is automatically captured. Disable Keep dubbing on this website to stop on navigation. Stop, closing the source tab, moving to another origin, the selected time limit or a safety failure ends capture. Navigation resets provider context, old speech/captions and delayed picture buffers; it does not reset the session time limit. Capture starts when you click Start. Closing the popup keeps your session running. Stop session ends capture. Your key is automatically saved as AES-GCM ciphertext in this browser profile and restored after restart, without a password or extra app. A non-exportable encryption key is kept in the same profile; this is not an OS keychain or protection against someone controlling the profile. Nothing is synced by Audivoya. Forget key stops capture and removes the encrypted record and in-memory cache. Stop keeps the saved key for reuse. During dubbing, selected-tab audio is sent directly to Google for processing. Google account terms and data-use policies apply; unpaid API audio may be used to improve Google's products. Audivoya has no developer-operated audio relay, advertising or automatic analytics upload. BEFORE YOU USE IT Translation quality and delay vary with the source, connection and provider. Word-perfect synchronization, instantaneous translation and support for every website or protected media are not guaranteed. Playback-speed detection depends on an observable main HTML player; some embedded or custom players may not expose it. Faster playback can reduce translation quality. Process only media you are permitted to use. Audivoya is an independent extension and is not affiliated with Google, Microsoft or the websites you visit. Setup guide: https://xuanquangit.github.io/audivoya/guide/ Privacy policy: https://xuanquangit.github.io/audivoya/privacy/ Support: https://xuanquangit.github.io/audivoya/support/ Publisher: Quang Vu Contact: xuanquang.work.it@gmail.com