Video Translate | AI Video Enhancement API

HeyGen Video Translate

HeyGen Video Translate is a powerful AI-powered video translation and dubbing model that automatically translates spoken content in videos into different languages — complete with lip-sync and natural voice cloning. Transform your videos for global audiences without reshooting.

Why It Stands Out

Full video translation: Automatically translates speech and generates new audio in the target language.
Lip-sync technology: AI adjusts lip movements to match the translated audio for natural-looking results.
Voice cloning: Preserves the original speaker's voice characteristics in the new language.
Multi-language support: Translate into English, Spanish, French, Hindi, Italian, German, Polish, Portuguese, Chinese, Japanese, Dutch, and more.
Simple workflow: Just upload a video and select your target language — no manual dubbing required.

Parameters

Parameter	Required	Description
video	Yes	Upload or link to the source video file.
output_language	Yes	Target language for translation (English, Spanish, French, etc.).

Supported Languages

English
Spanish
French
Hindi
Italian
German
Polish
Portuguese
Chinese
Japanese
Dutch
And more...

How to Use

Upload your video — drag and drop a file or paste a public URL.
Select output language — choose the target language for translation.
Click Run and wait for processing to complete.
Preview and download the translated video.

Best Use Cases

Global Content Distribution — Localize marketing videos, ads, and promotional content for international markets.
E-learning & Training — Translate educational videos and courses for multilingual audiences.
Social Media Expansion — Reach new audiences by translating viral content into multiple languages.
Corporate Communications — Distribute internal videos and announcements across global teams.
Entertainment & Media — Dub interviews, documentaries, and video content for foreign markets.

Pricing

Metric	Price
Per second of video	$0.0375 / s

Total cost = duration of video (in seconds) × $0.0375

Examples

30s video → 30 × $0.0375 = $1.125
60s video → 60 × $0.0375 = $2.25
5 min (300s) video → 300 × $0.0375 = $11.25
10 min (600s) video → 600 × $0.0375 = $22.50

Pro Tips for Best Quality

Use videos with clear speech and minimal background noise for optimal translation accuracy.
Single-speaker videos typically produce better lip-sync results than multi-speaker content.
Ensure the original audio is high quality — translation quality depends on accurate speech recognition.
For best lip-sync, use videos where the speaker's face is clearly visible and well-lit.

Notes

Ensure uploaded video URLs are publicly accessible.
Processing time varies based on video duration and current queue load.
Please ensure your content complies with usage guidelines.

Video Translate API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/heygen/video-translate with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Video Translate below.

HTTP example

# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/heygen/video-translate" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d '{
    "video": "https://example.com/your-input.mp4",
    "output_language": "English"
}'

# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY"

# When status is "completed", read the output from data.outputs[0].

Node.js example

// npm install wavespeed
const WaveSpeed = require('wavespeed');

const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env

const result = await client.run("heygen/video-translate", {
        "video": "https://example.com/your-input.mp4",
        "output_language": "English"
});

console.log(result.outputs[0]); // → URL of the generated output

Python example

# pip install wavespeed
import wavespeed

output = wavespeed.run(
    "heygen/video-translate",
    {
    "video": "https://example.com/your-input.mp4",
    "output_language": "English"
}
)

print(output["outputs"][0])  # → URL of the generated output

Video Translate API — Frequently asked questions

What is the Video Translate API?

Video Translate is a Heygen model for video editing, exposed as a REST API on WaveSpeedAI. HeyGen Video Translate: AI video translation into 70+ languages and 175+ dialects with no voice actors or dubbing. Fast, accurate, easy to use at $0.0375/sec. Ready-to-use REST API, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Video Translate API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/heygen/heygen-video-translate.

How much does Video Translate cost per run?

Video Translate starts at $0.037 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Video Translate accept?

Key inputs: `video`, `output_language`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/heygen/heygen-video-translate.

How long does Video Translate take to generate?

Average end-to-end generation time on WaveSpeedAI is around 140 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.

Can I use Video Translate outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (Heygen). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.

ExamplesView all

Related Models

README