Transform research papers and journals into audio with AI text-to-speech technology
AI video generator for text and image-to-video creation
Stage
Not given
Not given
Founded
Not given
Not given
Based in
US
Not given
Pricing model
Freemium
Paid
Pricing
Free trial for 3 days. Monthly plan: $12.99 USD per month billed monthly. Yearly plan: $4.92 USD per month ($59.00 billed yearly), saving 62% compared to monthly billing.
Standard Credit Pack: $50 for 2,500 credits; Pro Credit Pack: $100 for 6,000 credits; Max Credit Pack: $200 for 16,000 credits. All are one-time purchases with no recurring charge. Credits are consumed based on video duration and resolution; short 5-second videos are more efficient.
Key features
AI voice narration with 20+ realistic voices
Automatically skip citations, references, and footnotes
Listen at variable speeds from 0.75x to 3x
One-click note-taking with automatic transcription
Support for multiple file formats including PDFs, Word, EPUB, MOBI
Selective section listening for research papers
Zotero integration
Browser extension for saving articles
Cross-platform access on mobile, web, and desktop
Photo scanning to convert physical pages to audio
Text-to-video generation
Image-to-video generation
First-frame and end-frame controls
Multiple aspect ratios (21:9 to 9:16)
Three prompt expansion modes
480P and 768P resolution options
5-15 second video duration
Generation history and downloads
API access on Pro plans
What makes it different
Naturally-sounding AI voices that do not sound robotic
Specifically designed for academic papers with automatic citation and reference skipping
Accurately pronounces technical and scientific terminology
Integrated note-taking that captures key ideas without manual typing
Affordable pricing built for student budgets
Ranked #1 for image-to-video in independent evaluations (August 2026)
Fast generation times: 4.7s for text-to-video and 6.4s for image-to-video
Post-trained for stronger prompt adherence and aesthetics
Reference-guided generation for consistent subjects and styles
Focused workflow with clear controls and no recurring charges
Listening
MiniMax H3 Max