AI video model that creates cinematic shots with integrated sound from text and media references
Create original 15-second desk-concert videos from your photos with AI-generated music
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Freemium
Paid
Pricing
Free credits on sign-up (no card required). Subscription plans available monthly or yearly with 50% discount for annual billing. One-time credit packs available.
First take: $9.99 USD for 300 credits (1 video); Encore: $24.99 USD for 900 credits (3 videos); Session: $34.99 USD for 1500 credits (5 videos). Each 15-second 720p performance costs 300 credits.
Key features
Up to 50 multimodal references (30 images, 10 video clips, 10 audio files)
30-second unbroken camera takes
Multiple resolutions and aspect ratios
Synchronized audio generation with video
Precision editing mode for existing footage
Automatic lip-sync for dialogue
Commercial use rights on paid plans
Support for restyle, element replacement, and take extension edits
Reference tagging for precise control
Upload 1-5 portraits and assign musical roles
Choose vertical (9:16) or landscape (16:9) framing
Generate original AI music with soul-style accompaniment
Support for lead, keys, sax and backing vocal roles
15-second 720p MP4 video delivery
Private video storage with download controls
Subject matter customization (birthday, group chat, team victory)
Photo quality guidance and file validation
What makes it different
Single unbroken cinematic shot up to 30 seconds with integrated sound in one generation pass
Precision editing that changes only specified elements while preserving framing and motion
Up to 50 multimodal references for fine-grained control over character, location, and style simultaneously
Built by ByteDance, creators of leading social platforms
Original AI-generated music and lyrics, not voice cloning or existing recordings
Actual uploaded people appear, no fictional replacements
One-time credit packs with no automatic subscription renewal
Interactive storyboard showing exact structure before generation