Auto Dubbing
Upload clear narration — translate and dub it in one workflow.
Auto dubbing brings transcription, translation, and speech generation into one workflow. With automatic dubbing, you can adapt a complete recording without exporting every line yourself.
Three steps. A world of possibilities.
Less time on the timeline. More time on your next big idea.
One recording in.
Drop in your video or audio. Leave the speaker-by-speaker prep behind.
Choose your language.
Pick where your story goes next. We’ll translate the speech and create the voices.
A new audience out.
Preview the dub right here, then download it and share your story.
Your whole video. All its voices.
Built around the way you create, with a little less friction.
Your voice, one upload
Start with clear narration from one speaker. Upload the complete recording and choose a preset or cloned voice.
A voice for your story
Translated speech aligned with your recording’s timeline, so the new audio follows the story you already told.
From upload to preview
Get started without an account. Follow the progress, listen to the result, and download it on the same page.
What is automatic dubbing?+
Automatic dubbing turns the speech in a recording into another language, then aligns the translated audio with the original timeline.
Do I need to split a video by speaker?+
For this release, use one clear speaker per recording. Cloning uses reference speech from that recording.
Does auto dubbing copy the original voice?+
Choose cloning preview to use the original speaker’s voice, using clean reference speech from the recording. Preset voices are also available.
Can I dub a video with multiple speakers?+
The first release is intended for clear recordings with one speaker. Overlapping conversations are not supported.
What can I try for free?+
Try a short recording without an account after human verification. New accounts receive free credits once. See the pricing page for current trial limits and credit rates. Preview mode has no paid transactions.
Does DubbingNow preserve the original speaker’s voice?+
Choose cloning preview with clean reference speech from your recording. During testing, one saved voice is reused. Cloning quality is still being evaluated; preset voices remain available. Lip-sync editing is not provided.