video-translate_skill

This skill translates and dubs videos into multiple languages using HeyGen with lip-sync or audio-only options.
  • Python

2.5k

GitHub Stars

2

Bundled Files

2 months ago

Catalog Refreshed

3 months ago

First Indexed

Readme & install

Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.

Installation

Preview and clipboard use veilstrat where the catalogue uses aiagentskills.

npx veilstrat add skill openclaw/skills --skill video-translate

  • _meta.json471 B
  • SKILL.md10.7 KB

Overview

This skill translates and dubs existing videos into multiple target languages using HeyGen. It supports lip-synced dubbing, audio-only translation, multi-language batches, custom vocabulary and subtitle handling. Provide either a public video URL or a HeyGen video ID to start a translation job.

How this skill works

You create a translation job by calling HeyGen's /v2/video_translate endpoint with a video_url or video_id and the desired output_language(s). The API returns a translate_id which you poll until the job status is completed. When finished, the response includes a downloadable URL for the translated video or audio. Advanced options let you supply custom SRTs, vocabulary, speaker count, and toggles like audio-only, music removal, or speech enhancement.

When to use it

  • Translate an existing marketing, training, or product video into another language
  • Create lip-synced dubbed versions for international audiences
  • Produce faster audio-only translations when lip-sync is not needed
  • Generate multiple language variants in parallel for global distribution
  • Preserve brand terms or supply custom subtitles during translation

Best practices

  • Use high-quality source videos with clear speech for best results
  • Test with short clips before processing long videos to validate settings
  • Set speaker_num for multi-speaker content to improve speaker separation
  • Use translate_audio_only for faster turnaround when lip-sync isn't required
  • Provide a vocabulary list for product names or jargon to preserve exact terms
  • Allow up to 30 minutes per translation and use webhooks or polling to track progress

Example use cases

  • Localize a product demo into Spanish, French and Japanese using multi-language output
  • Convert interview footage to a dubbed version with lip-sync and voice cloning
  • Produce audio-only translated podcasts or voiceovers for distribution
  • Translate training videos and attach custom SRT subtitles for compliance
  • Batch-translate a content library into several languages for a global launch

FAQ

No. You can provide a public video_url or an existing HeyGen video_id when creating a translation job.

How long does a translation take?

Translation can take significantly longer than standard generation — allow up to 30 minutes per job depending on length and complexity.

Can I translate to multiple languages in one request?

Yes. The advanced v4 request supports output_languages to request multiple translations in a single call.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational
video-translate skill by openclaw/skills | VeilStrat