AI-powered platform to create audio and video podcasts from any content
Generative video models for animation
Stage
Not given
Not given
Founded
Not given
Not given
Based in
SG
US
Pricing model
Freemium
Not given
Pricing
Free plan with 50 credits (up to 12 min audio or 5 min video). Audio Creator at $9.9/mo with 300 credits/mo. Video Starter at $26/mo with 600 credits/mo. Creator Pro at $49/mo with 1,500 credits/mo.
Not given
Key features
AI script generation from documents, URLs, PDFs, notes and audio
Personalized AI podcast hosts created from photos
Voice cloning and natural AI voice selection
Audio and video podcast creation
Multiple podcast formats including solo, talk show and split-screen
Multi-speaker podcast support
Video rendering with captions and multiple formats
Direct publishing to YouTube, Spotify, Apple Podcasts and TikTok
Cartoon and pet host creation
Transcript generation and editing
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
Repurposes existing content into audio and video formats
Requires no editing experience to create polished podcasts
Complete end-to-end workflow from script to published episode
Customizable AI hosts and voices for brand consistency
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
PodcastorAI
Linum