Browser-based image and video generator with native audio in one unified workspace
AI video editor that turns long videos into viral shorts with auto-reframe, captions, thumbnails and multi-platform publishing
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Freemium
Freemium
Pricing
Free with 30 starter credits for new accounts. Paid plans: Basic $13.99/month (1,000 credits/month), Pro $19.99/month (3,000 credits/month), Max $74.99/month (15,000 credits/month). Yearly billing available with 30-50% savings.
Free plan with 10 processing minutes per month and 0 AI credits. Pro plan with 75 processing minutes per month and 35 AI credits per month. Social Pro plan with 150 processing minutes per month and 80 AI credits per month. Creator plan with 400 processing minutes per month and 200 AI credits per mon
Key features
Text-to-image generation from detailed prompts
Image editing with visual references
Text-to-video, image-to-video, and video-to-video generation
Native synchronized audio generation with video
Keyframe control for motion guidance
Multiple aspect ratios and quality levels up to 4K
Multilingual text and dialogue support
Video clips up to 20 seconds with audio
Connected workflow between image and video modes
Commercial usage rights on paid plans
Auto-reframe to 9:16 with AI speaker tracking
Animated karaoke captions with word-by-word animation
AI thumbnail generation with face-aware framing
Automatic silence and filler-word removal
Profanity beep and audio censoring
Voice-cloned dubbing and caption translation
Multi-platform publishing to 10 social platforms
UGC Studio AI actor videos
4K watermark-free exports
AI viral clip finder with virality scores
What makes it different
Unified multimodal workspace combining image generation, editing, and video creation with native audio in one tool
Native audio generation synchronized with video, including multilingual dialogue and event-linked sound
Direct workflow from concept to production without switching between separate tools
Keyframe and visual reference control for precise motion and style consistency
Speaker-tracked auto-framing: vertical crops follow the speaker across camera cuts for interviews and podcasts
Voice cloning for dubbing into Spanish and French with tone and emotion preservation
Flux 3 AI