AI voice-over generator and talking-head avatar video studio
Generative video models for animation
Stage
Not given
Not given
Founded
Not given
Not given
Based in
FR
US
Pricing model
Paid
Not given
Pricing
Audio minutes: 30 min at €7.50 excl. tax, 120 min at €24.00 excl. tax, 600 min at €90.00 excl. tax. Video minutes: 10 min at €25.00 excl. tax, 30 min at €60.00 excl. tax, 120 min at €180.00 excl. tax. Prices shown are excl. VAT; tax added at checkout.
Not given
Key features
Voice cloning from short audio samples
Talking-head avatar videos with synthesized speech
Available in English, French, German, Italian and Spanish
Asynchronous processing on dedicated GPUs
Shared credit pools for teams and organizations
Reusable avatars and voice libraries
Direct download and commercial use rights
Billed to the second for actual usage
No expiration on purchased credits
Secure Stripe payment processing
Pyramid-JiT (P-JiT) architecture with 32×32 token reduction
4× more aggressive token reduction than Linum v2
Converges in 11× fewer samples than Linum v2
2B-parameter model with frozen Qwen text encoder
Pixel-space diffusion with multi-resolution readouts
PixelREPA alignment with DINOv3-L
Curriculum learning over noise schedule
What makes it different
No subscription required, buy credits that never expire
Price decreases with larger packs
Everything runs in the browser with no software installation
Faithful voice cloning with timbre, pace and intonation preservation
Commercial use allowed for ads, courses, product videos and podcasts
Low-cost training: full 2B model trained for just $21K in compute
Controls baked into model training rather than post-hoc fine-tuning
Pixel-space compression without separate VAE bottleneck
Apache 2.0 open release with full model weights and code
Incarneo
Linum