HeyGen Video Translate — video translation | NetRoom

HeyGen Video Translate 1.0

HeyGen Video Translate translates speech in an existing video.

Category
Video
Modality
Text → Video
Context
—
Released
2026-04-01
Strengths

What it's the best tool for

  • Speech translation in an existing video
  • Source trimming and target-language selection
  • Speed and Precision workflows
  • Custom dub and subtitles in compatible modes
Limitations

When to reach for something else

  • A source video is required, not just a text prompt
  • Output depends on source-speech clarity
  • Review names, specialist terms and synchronisation
Sample output

How HeyGen Video Translate 1.0 responds

Prompt
Source: our paper-observatory video with stock English TTS narration. Source language en-US, target ru-RU, Speed mode, audio-only translation, MP4. Original speech: Small worlds. Big ideas. Bring your next story to life.
HeyGen Video Translate 1.0
Where teams use it

Four scenarios where it pays for itself

01
Language version
Adapt an existing publication for another audience.
02
Lesson segment
Translate a short self-contained learning section.
03
Narration localisation
Change spoken language without a lip-matching task.
04
Prepared dub
Supply a finished audio track in a compatible workflow.
About model

More about HeyGen Video Translate 1.0

HeyGen Video Translate: translation and localisation of existing video

HeyGen Video Translate translates speech in an existing video. It is a localisation workflow: provide the original clip and then choose the target language. It suits voice-over content, short lessons and multiple language versions of one publication.

Available in NetRoom

NetRoom offers Speed and Precision modes, audio-only translation or a lip-movement matching workflow, and clip trimming. You can also provide a finished dub and compatible subtitles. Frame-rate controls belong to the custom-audio workflow. MP4 is the verified output format.

Preparing the result

Upload a clip with intelligible speech and select the target language. Start with a short complete section so you can check translation and specialist pronunciation. Use audio-only translation for narration; lip matching is intended for a visible speaking subject. Listen through the result and review synchronisation before publishing.

Practical uses

  • Language version: Adapt an existing publication for another audience.
  • Lesson segment: Translate a short self-contained learning section.
  • Narration localisation: Change spoken language without a lip-matching task.
  • Prepared dub: Supply a finished audio track in a compatible workflow.

Reviewing the result

A source video is required, not just a text prompt; Output depends on source-speech clarity; Review names, specialist terms and synchronisation.

Recent changes

What changed HeyGen Video Translate 1.0

  • + Added video model HeyGen Video Translate 1.0 (HeyGen).
Full changelog →

Use HeyGen Video Translate 1.0 via the API

The same engine, straight from your code: one key and one balance for text, images, video and sound. Pay only for the requests you make.

curl
curl https://netroom.ai/api/v1/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "heygen/video-translate-10", "input": {"prompt": "A cinematic mountain sunrise"}}'

The model id is already in the example. The full parameter reference and prices live in GET /api/v1/models and in the docs.

API documentation Get an API key

Try HeyGen Video Translate 1.0
right now

Free access to basic models. No card, no obligations.