AI voice cloning and text-to-speech platform for creators, developers and teams
Free online tool to animate photos and videos using AI motion control
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Freemium
Freemium
Pricing
Free plan with 3,000 credits (valid 1 year) and 1,000 free credits monthly. Starter: $9.99/month (first month 50% off at $4.99) with 60,000 credits/month. Standard: $29.99/month (first month 50% off at $14.99) with 190,000 credits/month. Premium: $49.99/month with 320,000 credits/month. Monthly pass
Free tier with credits (amount not specified). One-time credit packs: Starter Pack $9.90 (110 credits), Creator Pack $29.90 (350 credits), Pro Pack $59.90 (580 credits). Standard quality uses 3 credits per second, Pro quality uses 4 credits per second.
Key features
Clone voice from 10-30 second audio sample in about 20 seconds
99% voice similarity for cloned voices
Support for 8 languages with one cloned voice
Text-to-speech with emotional control and adjustable speed/pitch
Online browser-based recording without extra software
Voice Square community library with thousands of voices
RESTful API for integration into apps and products
Long-form projects for audiobooks, podcasts and subtitle dubbing
Encrypted voice data storage with privacy protection
Motion transfer from 3-30 second reference videos
Full-body motion accuracy including hand gestures and facial expressions
Character orientation modes for image or video framing
Audio preservation from source videos
Prompt-guided refinement for backgrounds and lighting
Consistent character identity preservation across frames
HD export without watermarks
Motion Brush for localized motion control
Element Binding for multi-element facial alignment
Camera control for pan, tilt, dolly and zoom
What makes it different
Clone voice in 20 seconds from short sample
Real previews of every voice before use on Voice Square
Voice data remains encrypted and private, never shared with other users
Fair pricing with free credits and usage-based plans
Explicit motion extraction for predictable results instead of probabilistic generation
Professional animations created in 2-10 minutes instead of days or weeks
No motion-capture hardware or equipment required
Reduced trial-and-error through predictable motion control
Voice AI Labs
Animot