AI video generator that turns lyrics or a story into a finished video
Stage
Not given
Startup
Founded
Not given
2026
Based in
Not given
FR
Pricing model
Paid
Freemium
Pricing
Single Image: $1.99 per HD download. Starter: $14.99 (10 output credits + 10 included first previews). Growth: $59.99 (50 output credits + 50 included first previews). Pro: $179.99 (200 output credits + 200 included first previews). Standard photo HD download costs 1 credit. Video campaigns cost 2 c
Starter $22/month for 2,000 credits (about 2 full videos), Creator $49/month for 5,000 credits (about 4-5 full videos), Studio $129/month for 15,000 credits (about 12-15 full videos), Agency $399/month for 52,000 credits (about 40-52 full videos). Annual billing is 10% cheaper. Free accounts get 1,0
Key features
Catalog retouching with background cleanup and metal polish
Style reference matching for consistent collection presentation
Video campaign generation at 2-3 credits per 5 seconds
Free gold-tone correction for gold jewelry
14 video engine options including Kling 3, Veo 3.1, Hailuo 2.3, Seedance 2 and Gemini Omni Flash
113 visual styles or custom style descriptions
13 animation styles plus custom motion description
Songs composed and sung by Suno or ElevenLabs from lyrics, or upload your own mp3
Narrated story videos with ElevenLabs voices
Word-by-word audio sync so each scene matches what is sung or said
Consistent characters across scenes with up to 5 reference images
Dubbing of narrated videos into up to 5 languages per request
REST API and command-line tool for developers
Downloads without watermark on paid plans; free downloads carry small tubetube.io mark
What makes it different
Built specifically for jewelry with jewelry-focused instructions and detail-first output checks
Compare results against the actual piece before approving HD download
Free previews included with every credit pack before committing to download
Reflective metals and faceted gemstones handled with specialist jewelry photography focus
Automatic end-to-end video production from text in one run, handling music generation, storyboarding, scene generation, animation and editing
Maintains consistent characters and visual style across all scenes using sequential generation with reference images
Transparent credit system with automatic refunds for unused credits and failed generations
Real-time monitoring of every production step with live journal of all automated actions
Built by an active creator running real multilingual faceless YouTube channels on the same pipeline
Jewels Retouch
TubeTube