At least 1 image required · Max 5 · 10MB each · PNG, JPEG, WebP
Max 3 · 50MB each · MP4, WebM, MOV
Loading...
Max 10MB · PNG, JPEG, WebP
Recommended: 20–2000 characters for best results
0Cost: ~225 credits
Max 10MB each · PNG, JPEG, WebP · Up to 3 images
Recommended: 20–2000 characters
0Max 5000 chars. Best quality: 10–500
0Max 25MB. Formats: mp3, wav, m4a, flac, ogg
Max 5 minutes. Audio is recorded in your browser.
Paste a public audio URL (mp3, wav, m4a, flac, ogg). Max 5 min.
Custom voice: 2,000 credits per synthesis
Voice Clone
Clone any voice — yours, a celebrity, a character, or anyone — for text-to-speech generation.
Record 5–30 seconds of clear speech. Minimize background noise.
Drop audio file or click to browse
WAV, MP3, M4A, OGG, AAC — Max 10MB
This may take 1–5 minutes. You can leave this page.
How it works
- Training costs 10 credits per voice (no limit)
- Using a cloned voice for TTS costs 2,000 credits per synthesis
- Unused voices expire after 7 days; first TTS use activates permanently
- Record 5–30 seconds of clear speech for best results
See what AI can create
Bring your words to life as cinematic video
Your audio will appear here
Configure options on the left and click Generate
See what AI can create
Transform your ideas into stunning images with AI
Confirm Generation
Age Verification Required
Your prompt may generate adult content. You must confirm you are 18+ to proceed.
Please confirm your age to continue