AI voice generator for natural text to speech, voice cloning, and expressive audio
Generative video models for animation
Stage
Established
Not given
Founded
2020
Not given
Based in
US
US
Pricing model
Freemium
Not given
Pricing
Free plan includes 1,000 credits to start. Individual plan $19/month (billed $190 annually, 20,000 credits/month). Solo plan $39/month (billed $390 annually, 50,000 credits/month). Agency plan $99/month (billed $990 annually, 250,000 credits/month). Yearly plans include 2 months free.
Not given
Key features
1000+ AI voices across 142+ languages and accents
Text-to-speech with natural speech synthesis
Browser-based studio with no installation required
Commercial rights on all paid plans
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
Ultra-realistic AI voices powered by state-of-the-art neural TTS technology
Full commercial rights included on paid plans with no royalties
Generate voiceovers in seconds instead of hours
Trusted by 3.5 million users across 150+ countries
Works with all major video editing software
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
Listnr
Linum