Convert research papers into engaging audio experiences
Online AI image workbench for text-to-image, image-to-image, and reference-guided editing
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Freemium
Not given
Pricing
Free Trial: $0 forever, converts 5 papers with standard voice quality. Researcher Plan: $11 per month (or $8 per month billed annually at $96) with unlimited paper conversions and premium voice quality.
Starter Pack: $7.99 (150 credits); Growth Pack: $13.99 (300 credits); Professional Pack: $29.99 (900 credits); Enterprise Pack: $95.88 (3600 credits). All credits never expire. Payment methods include Alipay and WeChat Pay.
Key features
Convert research papers to audio with AI processing
Save time by listening while commuting or exercising
AI-powered explanations for complex formulas and figures
Intelligent chapter navigation to jump to specific sections
Export to Spotify, Apple Podcasts, and YouTube Music
Natural voice narration quality
Customizable knowledge level from beginner to expert
Support for PDF files and arXiv links
Automatic skipping of references and citations
Text-to-image and image-to-image generation with multiple AI models
Reference image-guided editing with prompt control
Portrait and avatar transformation
Product image transformation
Background replacement and style conversion
AI image editing tools: background removal, object erasing, text removal, old photo restoration
Image upscaling to 4K and recoloring
AI photo effects: age filter, cartoon conversion, sketch effect, vintage style
Prompt optimization and prompt library with 200+ AI tools
What makes it different
AI translates complex math, tables, and images into clear explanations without needing to read the paper
Export audio to podcast platforms for learning on-the-go
Chapter navigation allows selective listening to specific paper sections
Customized explanations from beginner to expert level
Preserves key subjects and composition while changing background, style, and lighting through reference-guided generation
Supports photos, text prompts, or combination of both for flexible input