Skip to content
Video & Audio
Skill

/video-translate

Translate and dub existing videos into multiple languages using HeyGen. Use when: (1) Translating a video into another language, (2) Dubbing video content with lip-sync, (3) Creating multi-language versions of existing videos, (4) Audio-only translation without lip-sync, (5)

From plugin
openmontage
80k49 skills4 commands

Claude Code

$ npx -y skills add openmontageinc/openmontage --skill video-translate --agent claude-code

SKILL.md

video-translate.SKILL.md
name: video-translate
description: |
  Translate and dub existing videos into multiple languages using HeyGen. Use when: (1) Translating a video into another language, (2) Dubbing video content with lip-sync, (3) Creating multi-language versions of existing videos, (4) Audio-only translation without lip-sync, (5) Working with HeyGen's /v2/video_translate endpoint.
allowed-tools: mcp__heygen__*
metadata:
  openclaw:
    requires:
      env:
        - HEYGEN_API_KEY
    primaryEnv: HEYGEN_API_KEY

Video Translation (HeyGen)

Translate and dub existing videos into multiple languages, preserving lip-sync and natural speech patterns. Provide a video URL or HeyGen video ID — no need to create the video on HeyGen first.

Authentication

All requests require the `X-Api-Key` header. Set the `HEYGEN_API_KEY` environment variable.

curl -X POST "https://api.heygen.com/v2/video_translate" \
  -H "X-Api-Key: $HEYGEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"video_url": "https://example.com/video.mp4", "output_language": "es-ES"}'

Default Workflow

1. Provide a video URL or HeyGen video ID 2. Call `POST /v2/video_translate` with the target language 3. Poll `GET /v2/video_translate/{translate_id}` until status is `completed` 4. Download the translated video from the returned URL

Creating a Translation Job

Request Fields

| Field | Type | Req | Description | |-------|------|:---:|-------------| | `video_url` | string | Y* | URL of video to translate (*or `video_id`) | | `video_id` | string | Y* | HeyGen video ID (*or `video_url`) | | `output_language` | string | Y | Target language code (e.g., `"es-ES"`) | | `title` | string | | Name for the translated video | | `translate_audio_only` | boolean | | Audio only, no lip-sync (faster) | | `speaker_num` | number | | Number of speakers in video | | `callback_id` | string | | Custom ID for webhook tracking | | `callback_url` | string | | URL for completion notification |

**Either** `video_url` **or** `video_id` must be provided.

curl

curl -X POST "https://api.heygen.com/v2/video_translate" \
  -H "X-Api-Key: $HEYGEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "video_url": "https://example.com/original-video.mp4",
    "output_language": "es-ES",
    "title": "Spanish Version"
  }'

TypeScript

interface VideoTranslateRequest {
  video_url?: string;
  video_id?: string;
  output_language: string;
  title?: string;
  translate_audio_only?: boolean;
  speaker_num?: number;
  callback_id?: string;
  callback_url?: string;
}

interface VideoTranslateResponse {
  error: null | string;
  data: {
    video_translate_id: string;
  };
}

async function translateVideo(config: VideoTranslateRequest): Promise<string> {
  const response = await fetch("https://api.heygen.com/v2/video_translate", {
    method: "POST",
    headers: {
      "X-Api-Key": process.env.HEYGEN_API_KEY!,
      "Content-Type": "application/json",
    },
    body: JSON.stringify(config),
  });

  const json: VideoTranslateResponse = await response.json();

  if (json.error) {
    throw new Error(json.error);
  }

  return json.data.video_translate_id;
}

Python

import requests
import os

def translate_video(config: dict) -> str:
    response = requests.post(
        "https://api.heygen.com/v2/video_translate",
        headers={
            "X-Api-Key": os.environ["HEYGEN_API_KEY"],
            "Content-Type": "application/json"
        },
        json=config
    )

    data = response.json()
    if data.get("error"):
        raise Exception(data["error"])

    return data["data"]["video_translate_id"]

Supported Languages

| Language | Code | Notes | |----------|------|-------| | English (US) | en-US | Default source | | Spanish (Spain) | es-ES | European Spanish | | Spanish (Mexico) | es-MX | Latin American | | French | fr-FR | Standard French | | German | de-DE | Standard German | | Italian | it-IT | Standard Italian | | Portuguese (Brazil) | pt-BR | Brazilian Portuguese | | Japanese | ja-JP | Standard Japanese | | Korean | ko-KR | Standard Korean | | Chinese (Mandarin) | zh-CN | Simplified Chinese | | Hindi | hi-IN | Standard Hindi | | Arabic | ar-SA | Modern Standard Arabic |

Translation Options

Basic Translation (with lip-sync)

const config = {
  video_url: "https://example.com/original.mp4",
  output_language: "es-ES",
  title: "Spanish Translation",
};

Audio-Only Translation (faster, no lip-sync)

const config = {
  video_url: "https://example.com/original.mp4",
  output_language: "es-ES",
  translate_audio_only: true,
};

Multi-Speaker Videos

const config = {
  video_url: "https://example.com/interview.mp4",
  output_language: "fr-FR",
  speaker_num: 2,
};

Advanced Options (v4 API)

For more control over translation:

interface VideoTranslateV4Request {
  input_video_id?: string;
  google_url?: string;
  output_languages: string[];        // Multiple languages in one call
  name: string;
  srt_key?: string;                  // Custom SRT subtitles
  instruction?: string;
  vocabulary?: string[];             // Terms to preserve as-is
  brand_voice_id?: string;
  speaker_num?: number;
  keep_the_same_format?: boolean;
  input_language?: string;
  enable_video_stretching?: boolean;
  disable_music_track?: boolean;
  enable_speech_enhancement?: boolean;
  srt_role?: "input" | "output";
  translate_audio_only?: boolean;
}

Multiple Output Languages

const config = {
  input_video_id: "original_video_id",
  output_languages: ["es-ES", "fr-FR", "de-DE"],
  name: "Multi-language translations",
};

Custom Vocabulary (preserve specific terms)

const config = {
  video_url: "https://example.com/product-demo.mp4",
  output_language: "ja-JP",
  vocabulary: ["SuperWidget", "Pro Max", "TechCorp"],
};

Custom SRT Subtitles

Read more
@calesthio
Ships withopenmontage

World's first open-source, agentic video production system. 12 production pipelines, 100+ tools, 700+ agent skill and production-knowledge files. Turn your AI coding assistant into a full video production studio.

Stars on GitHub

Momentum

stars in total
80.1k
Star history of calesthio/OpenMontage on GitHub, a chart by star-history.com

Other skills on openmontage.

acestep

acestep

AI music generation with ACE-Step 1.5 — background music, vocal tracks, covers, stem extraction for video production. Use when…

agents

agents

Build voice AI agents with ElevenLabs. Use when creating voice assistants, customer service bots, interactive voice characters,…

ai-video-gen

ai-video-gen

Generate AI videos from text prompts using multiple provider gateways. Use when: (1) Generating videos from text descriptions,…

avatar-video

avatar-video

Create AI avatar videos with precise control over avatars, voices, scripts, scenes, and backgrounds using HeyGen's v2 API. Use…

azure-speech-to-text

azure-speech-to-text

Transcribe audio to text using Azure AI Speech (Fast Transcription REST API). Use when converting audio/video to text, generating…

More skills from other plugins.

captions-overlay

captions-overlay

Overlay doctrine for captions in HyperFrames videos — the caption MODEL (drop / rail / embed) and the rule that captions are an…

@heygen-com@heygen-comInstall Skill
seedance-antislop

seedance-antislop

This skill should be used when a Seedance 2.0 prompt contains generic AI filler, hollow superlatives, vague cinematic language,…

@emily2040@emily2040Install Skill

Questions about video-translate.

Which coding agents can use video-translate?
video-translate installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.