Input Mode
Drop a cat image here
PNG, JPG, WEBP up to 10MB
Face Detected
PNG • 2048×2048 • 2.4MB
Speech Source
0 chars • Est. 0s
00:00
Click to start recording
Transcript:
Drop audio file or click to browse
MP3, WAV, M4A up to 50MB
recording.mp3
Lip Sync Settings
75%
90%
40%
Generation Summary
Review your configuration before generating
45 credits
Estimated cost
Asset
None selected
Voice
None selected
Duration
0s
Quality
Studio
Select a Voice
My Voices
0
No custom voices yet. Create one in the My Voice tab.
Library
AI Suggestions
Select a cat image to begin
Try "Mochi" voice for cute content
Use 9:16 format for TikTok/Reels
Brand Tips
- Close-up cat faces work best for lip sync
- Keep scripts under 30s for social media
- Use Studio Quality for final exports