Voice clone + lip-sync · free
Turn any photo into a realistic talking video
Upload a photo, upload a short voice sample to clone, write what they should say — we generate speech in that voice and animate the face so the mouth moves with the words. No paid API key required.
1. Upload photo
Full body or portrait works best. Face should be clear.
📷
Drop your photo here
or click to browse · JPEG, PNG, WebP · max 12MB
2. Voice sample (clone this voice)
Upload 10–30 seconds of clear speech. The generated voice will sound like this sample.
🎙️
Drop a voice sample here
or click to browse · MP3 / WAV / M4A · 10–30s clear speech works best
Tip: Record yourself saying a few natural sentences in a quiet room. Longer, cleaner samples clone more accurately. Without a sample, a generic neural voice is used.
3. Choose what they should do
Mood for the clip — speech + lip-sync still drive the mouth motion.
4. What they say & settings
Write the lines they should speak (cloned with your voice sample).
Duration
Resolution