Choose your video
Select an MP4, MOV or WebM with clear speech. Check the source audio in the local preview. Your file uploads when you choose to prepare the translation.
Turn spoken content in your video into English captions or an English AI voiceover. Compare a real example below, then try your own video.
Listen to the Chinese input and its English translation, then compare other language versions of the same product demonstration.
The Chinese input is our AI-dubbed demo over the original picture. Translated speech and captions are real outputs. These full-video examples are longer and higher resolution than the free 10-second preview. These examples use Fast dubbing, without voice cloning or lip sync.
Use these settingsFor a product demonstration, keep the original footage and decide whether your audience needs readable English captions or a new English voice.
Select an MP4, MOV or WebM with clear speech. Check the source audio in the local preview. Your file uploads when you choose to prepare the translation.
Use Subtitles only to keep the original audio, or Subtitles + voiceover with a standard AI voice such as Marin. Compare the example’s source and translated wording before choosing.
Check a free 10-second preview first. For a full conversion, sign in and use credits; review names, numbers and caption timing in the English MP4 and subtitle files.
Clear answers, no small print.
One accepted free preview per browser session is shared across the site, with no daily reset for that session. Additional limits are 2 per public IP and 20 site-wide per UTC day, resetting at 00:00 UTC. Accepted tasks, including failed tasks, use the allowance. Full videos require sign-in and credits.
No. The free English preview is up to 10 seconds at up to 480p, without a watermark. Paid full-video exports are also watermark-free. The demonstration below is a full-video example, not a free preview.
The editor shows an estimated processing range based on video length, output mode and queue. It is an estimate, not a deadline. Waiting includes transcription, translation, optional voice generation and rendering. The 15-second example describes video length, not processing speed.
Start with clear, single-speaker product demonstrations, tutorials or short introductions. Use one MP4, MOV or WebM up to 500 MiB, 30 minutes and 60 fps, with a playable audio track. Each dimension must be at most 1920 px and the frame at most 2,073,600 pixels. The public Chinese-to-English example shows one specific input; source-language accuracy is not guaranteed.
Paid full conversions include an MP4 with visible English captions and separate SRT and VTT files. Full video fits within 1280 × 720 px; a free preview fits within 854 × 480 px and includes only the MP4. Both preserve the source aspect ratio without enlarging smaller videos.
Check product names, measurements, numbers and the meaning of each sentence. Dubbing replaces the original audio, including music, and does not clone the speaker. Fast dubbing preserves the original lip movements; paid Lip Sync adjusts them to the translated voice. Captions use estimated timing within speech sections. Choose Subtitles only when retaining the original audio matters.