Introduction
VEED Lipsync 2.0 replaces what a person on screen appears to say. Pass the footage in video_url and the new speech in audio_url, and the mouth is redrawn to match.
Key features & highlights
Works on the take you already have
The rest of the frame stays as filmed: background, clothing and expression carry over, only the mouth area is re-rendered.
Resolution in, resolution out
The output keeps the frame size of the input video, and the price does not depend on it.
The audio decides the length
Shorter audio trims the clip; longer audio extends the picture to fit. In our tests the result matched the audio within a few hundredths of a second.
Request parameters
| Parameter | Required | Description |
|---|---|---|
video_url | Yes | Required. MP4 or WebM of one speaker with a visible face. at least 1 characters |
audio_url | Yes | Required. The new speech, up to five minutes. at least 1 characters |
Pricing
$0.084 / second
Billed per second of the new audio, rounded up to a whole second. The footage length and resolution do not change the price. Failed renders are not charged.
Use cases
Pick-up lines without a reshoot
Correct a name, a date or an offer in a recorded presenter clip.
Voice replacement
Put a translated or re-recorded voice track on the original performance.
Prompt guide & pro tips
One speaker, facing the camera
The model supports one speaker per clip. Keep the face visible and avoid fast head turns.
Clean audio
Use a single voice without music or background noise; clean a noisy recording first.
Match the pace
A new line close in length to the original keeps the body movement natural.
API quick start
# Generate the idempotency key once; reuse it when retrying after a lost response.
export SPICY_IDEMPOTENCY_KEY="${SPICY_IDEMPOTENCY_KEY:-$(uuidgen)}"
curl -X POST https://api.spicyapi.ai/api/v1/jobs/createTask \
-H "Authorization: Bearer $SPICY_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $SPICY_IDEMPOTENCY_KEY" \
-d '{
"model": "veed/lipsync-2.0/lip-sync",
"input": {
"audio_url": "https://example.com/reference.mp3",
"video_url": "https://example.com/reference.mp4"
}
}'
# Copy data.taskId from the response into TASK_ID, then poll the status.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.spicyapi.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
-H "Authorization: Bearer $SPICY_API_KEY"
See the API reference for authentication, the complete schema, polling, and error handling.




