HeyGen Video Translate
HeyGen Video Translate is a lip sync model that translates video content into different languages with matching lip movements.
Video translation with synchronized lip movements
HeyGen Video Translate is a lip sync model developed by HeyGen and made available through the Wavespeed provider. Released in September 2023, it takes a video URL as input along with a target output language selection, then produces a translated version of the video with lip movements synchronized to the new audio track. The model is priced at $0.0375 per second of video processed and supports a context window of 50,000 tokens.
The model is designed for use cases where video content needs to be localized for different language audiences without requiring a reshoot. By combining translation with lip sync, it addresses the visual mismatch that typically occurs when dubbed audio does not align with the speaker's mouth movements. It is well suited for content creators, businesses, and educators who need to distribute video material across multiple language markets.
What HeyGen Video Translate supports
Video Translation
Translates spoken content in a video into a selected output language, accepting a video URL as the primary input.
Lip Sync
Synchronizes the speaker's lip movements in the video to match the translated audio, reducing the visual mismatch common in dubbed content.
Language Selection
Accepts a dropdown-style language selector input, allowing users to specify the target output language for translation.
Per-Second Pricing
Billed at $0.0375 per second of video processed, making cost proportional to the length of the input video.
Ready to build with HeyGen Video Translate?
Get Started FreeCommon questions about HeyGen Video Translate
What inputs does HeyGen Video Translate require?
The model requires two inputs: a video URL pointing to the source video, and a language selection specifying the target output language.
How is HeyGen Video Translate priced?
The model is priced at $0.0375 per second of video processed. Costs scale directly with the duration of the input video.
What is the context window for this model?
HeyGen Video Translate has a context window of 50,000 tokens.
Who publishes HeyGen Video Translate and when was it released?
The model is published by HeyGen and was released in September 2023. It is available through the Wavespeed provider on MindStudio.
What type of model is HeyGen Video Translate?
It is a lip sync model, meaning it combines video translation with mouth movement synchronization so the speaker's lips match the translated audio.
Documentation & links
Parameters & options
Video to be translated.
Language to translate to.
Explore similar models
Start building with HeyGen Video Translate
No API keys required. Create AI-powered workflows with HeyGen Video Translate in minutes — free.