# Veed Lipsync v2 - Core.Today AI API

> Veed Lipsync v2 via Fal.AI. Replaces a source video's mouth movements to articulate a new audio track — takes any source video + a new audio track and produces a lip-synced output video.

- **Provider**: Veed
- **Model ID**: veed/lipsync/v2
- **Category**: Video Generation
- **Credits**: 2440 per video (flat rate, regardless of length)
- **Speed**: Medium
- **Quality**: High

## Features
- Re-syncs mouth movements in a source video to a new audio track
- Works with any source video + audio track pairing
- Output video length automatically matches the input video/audio
- Simple two-input workflow — no duration or resolution parameters to configure

## Use Cases
- Localizing a video into a new language by swapping in a translated audio track
- Re-recording or fixing narration without reshooting the original footage
- Dubbing presenter or influencer videos for different markets
- Updating a video's voiceover while keeping the original visual performance

## API Endpoint

Base URL: https://api.core.today/v1
Create Prediction: POST /predictions
Get Status: GET /predictions/{job_id}

## Authentication
Header: X-API-Key: YOUR_API_KEY

## Input Parameters

### Required
- **video_url**: string - Source video to lipsync
- **audio_url**: string - New audio track to articulate

## Examples

### Dubbing a presenter video into a new language
Swap a talking-head video's audio for a translated voiceover and get realistic lip movement matching the new track.
```json
{
  "model": "veed/lipsync/v2",
  "input": {
    "video_url": "https://v3.fal.media/files/monkey/q1fDPhrpfjfsaRmbhTed4_influencer.mp4",
    "audio_url": "https://v3.fal.media/files/rabbit/Ql3ade3wEKlZXRQLRbhxm_tts.mp3"
  }
}
```

### Fixing narration without a reshoot
Re-record a corrected narration track and apply it to the existing footage instead of reshooting.
```json
{
  "model": "veed/lipsync/v2",
  "input": {
    "video_url": "https://example.com/product-demo-source.mp4",
    "audio_url": "https://example.com/product-demo-narration-v2.mp3"
  }
}
```

## Response Format
```json
{
  "job_id": "abc123",
  "status": "pending | processing | completed | failed",
  "result": "URL or data (when completed)"
}
```

## Usage Flow
1. POST /predictions with model and input -> receive job_id
2. GET /predictions/{job_id} -> poll until status is completed or failed
3. Result contains output URL(s)

## Tips
- Works best when the source video's mouth is clearly visible and front-facing throughout.
- The output length always matches the source video/audio, so trim both to the segment you actually want dubbed.
- Use TTS or professionally recorded audio for the new track — cleaner audio produces more accurate lip movement.
- This is a redub tool, not a full talking-head generator — it only replaces mouth articulation on existing footage.

## Documentation
https://fal.ai/models/veed/lipsync/v2