Pascual AnyDub, end to end.

Yandex renders a natural-sounding dub of the whole video and AnyDub plays it over the original, ducking the source audio so both stay audible.

Best for: videos you want to actually enjoy rather than merely follow. The voice sounds human, not synthetic.

Trade-off: the first request for a given video has to be rendered from scratch, which can take up to a couple of minutes. Source-language support is limited (see below).

Takes the subtitles the video already has, translates them, and speaks them with either a regular system voice or a higher-quality Edge AI voice.

Best for: starting immediately. There is nothing to render, so playback begins within a second or two, and it works on far more sites and languages than the AI voice-over.

Trade-off: the video must have subtitles in the first place. Regular system voices are unlimited but can sound synthetic; Edge AI voices sound more natural and use the shared AI-voice allowance.

Captures the tab's audio and transcribes it locally with a speech-recognition model, then translates and speaks the result. Nothing about the audio leaves your computer for recognition.

Best for: live streams, and any video with no usable subtitles at all. It works with any spoken language.

Trade-off: it runs on your hardware, so it needs a moment to load the model on first use and follows speech with a short delay.

Open the voice selector in CC, LIVE or TEXT and choose a voice from the Edge AI group. These neural voices sound more natural than the regular Google, Microsoft or browser system voices while keeping the fast start of subtitle and live translation.

Voice, volume and speech speed can be adjusted for the active mode. TEXT keeps its own settings, so changing the voice used to read an article does not replace the voice you selected for video.

Edge AI voice time is shared across CC, LIVE and TEXT. The popup shows the remaining allowance, and time is counted only while an Edge voice is actually speaking.

If no AI-voice minutes remain, AnyDub automatically switches to a regular system voice instead of stopping the translation. Additional AI-voice minute packs are available in the Account tab; purchased minutes are attached to your account and do not expire.

In TEXT mode, audio produced with an Edge AI voice can be downloaded as an MP3. Browser system voices are played directly by the browser and therefore cannot be exported as an audio file.

Select text on any page, right-click it, open AnyDub, and choose Translate and read aloud. The same menu also offers Read aloud only and Translate only.

Right-click an empty part of a page and choose Read this page when you want AnyDub to process the page instead of a small selection.

Open the TEXT tab to choose the translation language, voice, volume and reading speed. You can also decide whether the translated text should remain visible while it is being read.

The on-page reader controls let you pause, resume or stop without returning to the extension popup.

Download the original text, the translation, or both languages together. If an Edge AI voice is selected, you can also save the generated speech as an MP3.

By default the on-screen subtitles mirror whatever the active engine produced. Turn on Yandex subtitles in the CC tab and AnyDub instead requests Yandex's own subtitle track, which carries its own timings.

You can tell them apart at a glance: language badges turn red when the lines come from Yandex, and stay violet otherwise.

With the checkbox on, CC speaks the Yandex lines rather than its own. That matters because the two tracks are split differently — using Yandex timings keeps the speech aligned with what is actually being said.

The subtitle overlay can show the translation, the original, both stacked, or a teleprompter view. Drag it anywhere over the video; the position is remembered separately for fullscreen and windowed playback.

The subtitles tab has a Download subtitles section at the bottom. SRT keeps the timings and loads into any player or editor; TXT is plain text for reading or pasting into a document.

You can save the translation on its own, the original on its own, or both stacked in one file. Start the translation first — the file contains exactly the lines that are on screen, whether they came from Yandex, the CC engine or live recognition.

Yandex officially supports eight source languages: English, German, French, Spanish, Italian, Chinese, Japanese and Korean. On these, both the AI voice-over and the subtitles are dependable.

A few more — Arabic, Lithuanian, Latvian — are accepted but undocumented. They often work, yet subtitle coverage can be thin: on some Arabic videos only about a third of the runtime comes back with lines, leaving long silent gaps. That is a limit of the source, not a fault in the extension. Switch to LIVE for those languages — local recognition does not care which language is being spoken.

Not every video has subtitles, and no amount of retrying will conjure them. When AnyDub reports that none are available, LIVE is the mode that still works — it listens to the audio directly.

The first time anyone requests a dub for a particular video, it is rendered from scratch. Afterwards the same video starts instantly for everyone, which is why a popular video feels immediate and an obscure one does not.

The overlay shows what is happening rather than a frozen line: a pulsing indicator with an attempt counter while the request is in flight, and a progress counter while subtitles are being translated.

A stream has no finished audio track to render, so the AI voice-over cannot apply. LIVE is built for exactly this case.

AnyDub re-syncs automatically after seeking, pausing or changing playback speed. If it still drifts, stop and start the dub again — that reloads the track against the current position.

The panel has separate volume controls for the dub and for the original audio. Lower the dub or raise the original until the balance suits you; the setting is remembered.

That usually means CC, LIVE or TEXT is using a regular system voice. Open that mode's voice selector and choose an Edge AI voice for more natural speech. VIDEO mode also uses a rendered AI voice when it is available for the video.

AnyDub attaches to standard video players, so most sites work. On unusual players the control may sit as a floating pill rather than inside the player bar. If a site still shows nothing, tell us and we will look at it.

For the AI voice-over and for Yandex subtitles, the video's address is sent so the track can be produced. For CC, subtitle text is sent for translation. In LIVE mode speech recognition runs entirely on your computer, while recognised text is sent for translation.

TEXT mode sends the selected text for translation when translation is requested. When an Edge AI voice is selected in CC, LIVE or TEXT, the text to be spoken is also sent for voice synthesis. Regular system voices are generated by the browser instead.

AnyDub does not upload your video, your microphone or your browsing history. The full statement is on the privacy page.