HeyGen Lipsync Speed overview
HeyGen Lipsync Speed by HeyGen
HeyGen built Lipsync Speed as the faster mode of its lipsync model. It is designed for lower-fidelity synchronization than Precision mode.
HeyGen Lipsync Speed specs
- Model ID
heygen/lipsync-speed- Developer
- HeyGen
- Input
- Image, Text, Video
- Output
- Video
- Endpoint
POST https://api.aimlapi.com/v2/video/generations
Dialogue replacement only
The model takes an existing video and a separate audio track that you provide. It performs dialogue replacement only. It does not translate speech and it does not generate audio.
Finish and approve the new audio before you submit the clip, because the model will use it as given.
Choose footage that suits Speed mode
HeyGen recommends Speed mode particularly for mostly front-facing videos with little facial occlusion. It also names one speaker or simple conversations as the best fit.
HeyGen recommends the mode for rapid drafts, previewing edits, batch processing and iterating before a final render. Start with a front-facing clip of a single speaker, then check the mouth movement in the output before you queue a larger batch.
Speed or Precision
HeyGen Lipsync Precision re-voices a video with higher-accuracy lip movement driven by avatar inference. Speed mode gives up some of that fidelity to return results faster.
Run your drafts through Speed. Send the same clip and audio to Precision for the final render if the mouth shapes in the draft look off.
Use cases
Preview a new voice-over on a finished video before approving a final render.
Re-voice a batch of single-speaker, front-facing clips with updated narration.
Iterate on script edits by swapping in revised audio and checking the lip match.
Replace the dialogue in a simple two-person conversation with a new recording.
HeyGen Lipsync Speed API pricing
| Usage | Price | Unit |
|---|---|---|
| Video generation | $0.014 |
Prices from the AI/ML API price list, checked on Nov 12, 2026.
How to use the HeyGen Lipsync 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/lipsync-speed",
"video_url": "https://example.com/input.mp3",
"audio_url": "https://example.com/input.mp3"
}'import os
import requests
headers = {
"Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
"Content-Type": "application/json",
}
payload = {
"model": "heygen/lipsync-speed",
"video_url": "https://example.com/input.mp3",
"audio_url": "https://example.com/input.mp3"
}
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/lipsync-speed",
"video_url": "https://example.com/input.mp3",
"audio_url": "https://example.com/input.mp3"
}),
});
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 Lipsync Speed
HeyGen Lipsync Speed FAQ
How much does HeyGen Lipsync Speed cost?
HeyGen Lipsync Speed costs $0.014 / sec on AI/ML API.
Does HeyGen Lipsync Speed translate or create the new audio?
No. It performs dialogue replacement only. You supply the finished audio track yourself.
What inputs does it need?
It needs an existing video and a separate audio track that you provide. The speaker's mouth is re-animated to match that audio.
Which videos work best in Speed mode?
HeyGen recommends mostly front-facing videos with little facial occlusion. One speaker or a simple conversation suits it best.
When should I switch to HeyGen Lipsync Precision?
Switch for the final render when you need higher-accuracy lip movement. Precision uses avatar inference, while Speed is meant for drafts, previews and batch work.
What is the HeyGen Lipsync Speed model ID?
Use heygen/lipsync-speed as the model parameter. Requests go to https://api.aimlapi.com/v2/video/generations with your AI/ML API key.