Step-by-step guides for video translation, image translation, main and detail image generation, model and scene image generation, and the browser extension

Here we take voice recognition translation as an example: select the languages you need and upload the video.

AI dubbing is enabled by default. Click the panel on the right of the dubbing option to preview voices in a pop-up and pick the one you like.

Enabling background music removes the vocals from the original audio by default — it strips the narration while keeping the music and sound effects. You can also pick a track from our music library.


Turn subtitles on or off as needed. When enabled, the subtitle style and position are fully customizable.


Once the upload is complete, the video starts translating.

After translation, you can preview and download the video directly, or edit it further. Click the 【Edit】button to open the video translation workbench.

Click any subtitle or text and an 【Edit Subtitle】 pop-up appears on the right. In the text editing area you can modify the content, font, size, color and more of the selected subtitle.

Click 【Dubbing Settings】 to adjust the voice-over of subtitles. After modifying the subtitle content or dubbing settings, click 【Preview】 to regenerate the updated voice-over audio and replace the automatic dubbing.

If a title should not be read aloud, or a line is skipped, click that subtitle to toggle between voiced subtitle and plain text (you can switch back and forth freely).


When everything looks good, click the 【Export】button in the top-right corner, choose the quality you need and export the video for publishing.
