Header Logo

Docs

Start

Header Logo

Start

Header Logo

Docs

Start

All Models

HeyGen logo

HeyGen Video Translation

HeyGen Video Translation translates speech in existing footage, preserving the speaker’s voice and combining translated dubbing with lip sync for localized video.

Video editing

Based on verified input duration.

OfferingPrice (USD)
Mode: speed$0.04 / input second
Mode: precision$0.08 / input second
  • Output Language: 178 listed options (same price).
  • Based on the video input; billing steps apply in this order:
  • Round input duration up to a whole second.
  • Cap billed duration at 120 seconds.
  • Round the total charge up to the next $0.01.

HeyGen Video Translation

HeyGen Video Translation localizes spoken content in an existing video. The source footage supplies the speech and on-screen performance, and a target language determines the translated version. The model combines translated dubbing with voice preservation and lip sync.

These capabilities address both the sound and visible delivery of speech. The translated voice retains the speaker’s vocal identity, while mouth alignment connects the localized audio to the person on screen. This keeps the original presenter central to the translated edition.

What it's good for

Training teams can adapt presenter-led lessons for audiences who speak another language. Product walkthroughs and educational explanations can keep their familiar spokesperson while making the spoken material accessible to a different audience.

Marketing teams can localize a spokesperson’s campaign footage, and internal communications teams can translate recorded announcements. The existing performance provides the basis for each language edition, preserving continuity with the source video.

Model ID

heygen/video-translate

Output Type

Video

Pricing

From $0.04 / input second

Provider

HeyGen

Hosting

Passthru

HeyGen Video Translation

HeyGen Video Translation localizes spoken content in an existing video. The source footage supplies the speech and on-screen performance, and a target language determines the translated version. The model combines translated dubbing with voice preservation and lip sync.

These capabilities address both the sound and visible delivery of speech. The translated voice retains the speaker’s vocal identity, while mouth alignment connects the localized audio to the person on screen. This keeps the original presenter central to the translated edition.

What it's good for

Training teams can adapt presenter-led lessons for audiences who speak another language. Product walkthroughs and educational explanations can keep their familiar spokesperson while making the spoken material accessible to a different audience.

Marketing teams can localize a spokesperson’s campaign footage, and internal communications teams can translate recorded announcements. The existing performance provides the basis for each language edition, preserving continuity with the source video.