Skip to main content

Overview

Lip Sync synchronizes lip movements in videos with new audio tracks using advanced AI motion analysis. The API creates realistic lip-sync animation that matches speech patterns, timing, and mouth movements for natural-looking results. Processing: See recent typical API-job times. Jobs run asynchronously, and duration varies with the input, selected settings, and queue load.

How It Works

  1. Provide a source video - Upload the video with the person speaking
  2. Provide audio - Upload the new audio track to sync to
  3. API processes the video - AI analyzes audio and animates lip movements
  4. Download the result - Retrieve your lip-synced video

Use Cases

For a complete voice-to-video workflow, follow the lip-sync starter recipe. It covers uploading your video and voiceover, submitting the lip-sync job, and downloading the result.
  • Dubbing and localization - Translate videos to new languages with matching lips
  • Personalized messages - Create custom video messages with any voice
  • Educational content - Produce training videos with voiceovers
  • Entertainment - Create fun lip-sync content for social media
  • Accessibility - Add voiceovers to silent video content

Best Practices

Video Requirements

Clear, front-facing footage works best - Ensure the speaker’s face and lips are clearly visible throughout.
  • Face visibility - Full face visible with minimal obstructions
  • Good lighting - Even lighting on the face
  • Stable framing - Face stays in frame throughout
  • Moderate motion - Avoid extreme head movements

Audio Requirements

  • Clear speech - Well-recorded audio without background noise
  • Set start_seconds and end_seconds to select the clip and provide enough audio for that segment.
  • Supported formats - MP3, WAV, AAC, FLAC, M4A, OPUS, OGG/OGA, WEBM/WEBA, AIFF, AMR
  • Natural pacing - Normal speaking pace for best results

Matching Audio to Video

Code Examples

Basic Lip Sync

Pricing

Lip Sync is charged per rendered frame, and the rate depends on style.generation_mode: For example, a 10-second clip capped at 30 FPS in lite mode costs about 300 credits. Use max_fps_limit to lower the frame rate and reduce cost. Credits are only charged for the frames that actually render, and the completed job’s credits_charged shows the exact cost.
Try this in our Google Colab Cookbook: Run this API with sample code. Just add your API key.

API Reference

Lip Sync API Reference

View full API specification

AI Voice Generator

Generate speech audio for your videos

Face Swap Video

Replace faces in videos