Lipsync API — Sync Video Characters to Audio

Lip-sync video characters to an audio track. Modify lip movements in AI-generated or real video to match voiceover narration. Tiered pricing from 50 credits. Max 30s.

New: Lip-sync video characters to any audio track with a single API call. Works with AI-generated characters, animation, and live-action footage.

Pricing

Tiered by video duration. Video is probed automatically before processing.

Duration	Credits	Price (Pro Yearly)	Price (Pro Monthly)
≤5s	50	$0.30	$0.40
≤10s	100	$0.60	$0.80
≤15s	150	$0.90	$1.20
≤20s	200	$1.20	$1.60
≤25s	250	$1.50	$2.00
≤30s	300	$1.80	$2.40

Formula: ceil(duration / 5) × 50 credits. Maximum video duration: 30 seconds.

Credits are deducted upfront based on video duration. Refunded automatically if lipsync fails.

Endpoint

POST https://vicsee.com/api/v1/tools/lipsync

See Authentication for API key setup.

Parameters

Parameter	Type	Required	Description
video_url	string	Yes	Source video URL (MP4, MOV, WebM, M4V, GIF). Max 30 seconds.
audio_url	string	Yes	Audio track URL (MP3, WAV, AAC, OGG, M4A)
sync_mode	string	No	How to handle duration mismatch. Default: `"cut_off"`.

Sync Modes

Mode	Behavior
`cut_off`	Truncates whichever input is longer (default, most predictable)
`loop`	Repeats the video to match longer audio
`bounce`	Palindrome playback of video to match audio length
`silence`	Extends video with frozen frames if audio is longer
`remap`	Time-stretches the video to match audio duration

Example Request

curl -X POST https://vicsee.com/api/v1/tools/lipsync \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "video_url": "https://example.com/scene.mp4",
    "audio_url": "https://example.com/voiceover.mp3"
  }'

Response

{
  "success": true,
  "data": {
    "id": "task_abc123",
    "model": "lipsync",
    "status": "completed",
    "output": {
      "url": "https://cdn.vicsee.com/results/dew/user-id/abc123.mp4",
      "duration": 5.0
    },
    "creditsUsed": 50,
    "creditsRemaining": 450,
    "createdAt": "2026-03-01T12:00:00.000Z"
  }
}

The response returns after processing completes (typically 30-120 seconds depending on video length). The output URL contains the lip-synced video hosted on VicSee CDN (available for 7 days).

Pipeline Example

Generate a voiceover with ElevenLabs, then lip-sync it to an AI-generated video:

# Step 1: Generate voiceover
AUDIO=$(curl -s -X POST https://vicsee.com/api/v1/generate \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "elevenlabs-v3-dialogue",
    "prompt": "Welcome to the future of AI video creation."
  }' | jq -r '.data.output.url')

# Step 2: Lip-sync the voiceover to your video
curl -X POST https://vicsee.com/api/v1/tools/lipsync \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d "{
    \"video_url\": \"https://example.com/ai-generated-scene.mp4\",
    \"audio_url\": \"$AUDIO\"
  }"

Limits

Constraint	Value
Maximum video duration	30 seconds
Supported video formats	MP4, MOV, WebM, M4V, GIF
Supported audio formats	MP3, WAV, AAC, OGG, M4A
Max processing time	5 minutes
Multi-person support	Yes (active speaker detection)
AI-generated characters	Yes

Errors

Code	HTTP	Description
`MISSING_VIDEO_URL`	400	`video_url` not provided
`MISSING_AUDIO_URL`	400	`audio_url` not provided
`INVALID_SYNC_MODE`	400	Sync mode not one of the valid options
`PROBE_FAILED`	422	Could not read video duration
`VIDEO_TOO_LONG`	422	Video exceeds 30 second maximum
`INSUFFICIENT_CREDITS`	402	Not enough credits
`LIPSYNC_SUBMIT_FAILED`	500	Failed to submit to Replicate
`LIPSYNC_FAILED`	500	Processing failed or timed out

ElevenLabs Audio — Generate voiceover audio to lip-sync
Merge Audio + Video — Merge audio and video without lipsync
Merge Videos — Combine multiple videos into one
Tasks API — Check task history
Credits API — Check your credit balance

Lipsync

On this page