HeyGen Video Translation Speed overview
HeyGen Video Translation Speed by HeyGen
HeyGen built this mode to translate a video into 170+ languages with lip sync. HeyGen states that it keeps the speaker's voice and synchronizes the lips to the target language.
HeyGen Video Translation Speed specs
- Model ID
heygen/video-translation-speed- Developer
- HeyGen
- Input
- Image, Text, Video
- Output
- Video
- Endpoint
POST https://api.aimlapi.com/v2/video/generations
What speed mode trades away
HeyGen designed speed mode for workflows where processing time matters more than perfect lip sync. Against Precision mode, HeyGen says it gives standard rather than high lip-sync quality and adequate rather than context- and gender-aware translation.
HeyGen recommends speed mode for faces with little movement. For significant movement, side angles or facial occlusions, HeyGen recommends Precision mode instead.
Two options for the audio you get back
The disable music track option removes the background music from the result. Turn it on when the source has a music bed that you do not want under the dubbed voice. Leave it off when the music belongs to the finished video.
The enable speech enhancement option improves the speech quality of the result. Start with it on for sources recorded in noisy rooms, then compare a short clip with and without it.
Speed, Precision or Audio Only
HeyGen Video Translation Precision uses avatar inference for higher-accuracy lip sync. HeyGen Video Translation Audio Only dubs the video and keeps the original picture without lip sync. Run one clip with a moving face through Speed and Precision and check the mouth shapes before you choose a mode for a batch.
Use cases
Dub a batch of talking-head training videos into several languages in one run.
Localize short product or social videos where the speaker faces the camera with little movement.
Produce quick translated drafts of interviews before deciding which ones deserve a Precision pass.
Replace noisy or music-heavy source audio with cleaner dubbed speech by using the music and speech enhancement options.
HeyGen Video Translation Speed API pricing
| Usage | Price | Unit |
|---|---|---|
| Video generation | $0.013 |
Prices from the AI/ML API price list, checked on Nov 12, 2026.
How to use the HeyGen Video Translation Speed API
View docs
Build with your agent
Give your agent the model details, code and documentation.
1Get your API key
Create API keyexport AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"2Make your first request
curl 'https://api.aimlapi.com/v2/video/generations' \
-H "Authorization: Bearer $AIMLAPI_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "heygen/video-translation-speed",
"video_url": "https://example.com/input.mp3",
"output_language": null
}'import os
import requests
headers = {
"Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
"Content-Type": "application/json",
}
payload = {
"model": "heygen/video-translation-speed",
"video_url": "https://example.com/input.mp3",
"output_language": null
}
response = requests.post("https://api.aimlapi.com/v2/video/generations", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())const response = await fetch("https://api.aimlapi.com/v2/video/generations", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "heygen/video-translation-speed",
"video_url": "https://example.com/input.mp3",
"output_language": null
}),
});
if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());The request returns a generation id. Poll GET https://api.aimlapi.com/v2/video/generations?generation_id=<id> until the status is completed.
Models similar to HeyGen Video Translation Speed
HeyGen Video Translation Speed FAQ
How much does HeyGen Video Translation Speed cost?
HeyGen Video Translation Speed costs $0.013 on AI/ML API, billed as you go with no subscription.
What does this model take as input and return?
It takes image, text and video input and returns a video. The result is the source video dubbed into the target language with lip sync.
Which request options can I set?
Two options are available, each true or false. Disable music track removes the background music, and enable speech enhancement improves the speech quality of the result.
When should I use Precision mode instead?
HeyGen recommends Precision mode for significant movement, side angles or facial occlusions. Speed mode suits faces with little movement.
Can I keep the original picture and only dub the audio?
Use HeyGen Video Translation Audio Only for that. It dubs the video and keeps the original picture without lip sync.
What is the HeyGen Video Translation Speed model ID?
Use heygen/video-translation-speed as the model parameter. Requests go to https://api.aimlapi.com/v2/video/generations with your AI/ML API key.