Multimodal AI video generation platform for creators
Stage
Established
Not given
Founded
2018
Not given
Based in
GB
Not given
Pricing model
Paid
Freemium
Pricing
Pay-as-you-go credits: 30 minutes for $6 USD ($0.20/minute), 300 minutes, 1000 minutes, 2500 minutes, or 10000 minutes. Prices per minute decrease with larger packages. Educational and non-profit discounts available.
Basic Yearly: $24.99/month or $299.90/year, includes 2,500 credits per month, up to 110 seconds of video generation at 1080p resolution with sound effects and standard processing. Credit packs available for additional usage.
Key features
Text to speech in 100 languages with 900 voices
Convert PowerPoint or Markdown to video
Speech to text transcription
Convert subtitles to synchronized audio
Automatic video production automation via API
Edit videos as easily as editing text
Automatic subtitles and closed captions
Batch audio and video creation
Text-to-video generation with natural language control
Image-to-video animation from uploaded or referenced images
Reference-guided video workflows with @tag system
Multi-shot continuity with consistent characters and environments
Advanced scene editing and seamless extensions
Audio-visual synchronization
First and last frame control with camera guidance
Multiple video model options including Seedance 2.5
Batch generation for up to 4 video variations
AI image generation tools for creative projects
What makes it different
No need to record or re-record narration
Consistent audio across script updates
Automatic synchronization of audio and video
Combines multiple input modes—text, images, video, and audio—in one unified workflow for comprehensive creative control
Director-level control with reference guidance, frame control, and camera movement direction
Maintains visual consistency across multi-shot sequences and extended scenes
Seamless scene extension preserving motion and cinematic flow without restarting
Independent platform with automated content moderation and responsive support