AI video clipper that converts YouTube podcasts into viral short-form clips with dynamic captions
Generative video models for animation
Stage
Startup
Not given
Founded
2025
Not given
Based in
CN
US
Pricing model
Paid
Not given
Pricing
Starter Pack: $10 USD for 100 credits (processes approximately 6.7 hours of video). Creator Pack: $30 USD for 350 credits including 50 bonus credits (processes approximately 23.3 hours of video). Pro Pack: $50 USD for 650 credits including 150 bonus credits (processes approximately 43.3 hours of vid
Not given
Key features
Auto-face tracking to center the speaker and convert 16:9 to 9:16 format
Hook-Body-Payoff structure enforcement to reject weak clip starts
100% watermark-free exports ready to post directly
Full transcripts and SRT file downloads included
Detailed reasoning report explaining viral potential and scoring
1080p HD video quality rendering
Processing of videos up to 2 hours long
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
Pay-as-you-go pricing at 0.25 credits per minute with no monthly subscriptions or usage pressure
Specialized AI trained for podcast and interview content rather than generic video editing
Credits never expire, allowing flexibility in when content is processed
Guaranteed hook and payoff structure in every clip versus random cuts
Automatic restoration of credits if processing fails due to system error
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
PodClip AI
Linum