P-Video-2 Pro
MiniMax H3 accelerated by Pruna: up to 9 images, 3 clips and 3 audio references, and the take back in seconds, at 480p or 768p.
from ⚡ 660 Synapses per take
- up to 15s
- up to 768p
- native sound
- takes references
- Locked character
- Native sound
Paste it into Claude and that's it.
With the house MCP on, your agent finds P-Video-2 Pro by name, quotes the cost first and generates on your account. Swap the scene for yours.
How to connect →Use Sapiens to make a video take with P-Video-2 Pro: slow camera rising up the face of a lighthouse in the desert, late afternoon, dust in the air. Before generating, tell me how many Synapses it will cost.
More video engines
See all →- Video
VEO 3.1
GoogleHigh fidelity, cinematic, native audio.
up to 8s · takes references
from ⚡ 12,500 per take 
Video@borderlessGemini Omni
GoogleText, image or a video of yours: generates, edits and extends up to 10 s, from 360p to 4K, with native audio.
up to 10s · up to 4K · takes references · extends the take
from ⚡ 560 per take
Video@borderlessSeedance
ByteDanceCinematic with native audio, 4 to 15s. Takes references and a motion video.
- 2.0
- 2.0 Fast
- 2.0 Mini
- 2.5
up to 30s · up to 1080p · native sound · takes references
from ⚡ 800 per take
If it resonated,
we talk.
Screening by resonance. A real conversation, entry by curation. And what you build inside comes out published, with an address of its own.
Prefer Telegram? Talk there →Human screening within 48h. Direct communication, one on one.