AI writing partner for fiction that helps novelists draft, describe, rewrite, and finish books while keeping their own voice
Know which headline wins before you spend traffic on it.
Stage
Established
Not given
Founded
2020
Not given
Based in
Not given
Not given
Pricing model
Free trial
Not given
Pricing
Not given
Free: $0/month with 5 rankings and 60 Claude-written options monthly. Creator: $19/month with 100 rankings and 2,500 options. Pro: $49/month with 600 rankings and 6,000 options. Agency: $149/month with 3,000 rankings and 20,000 options.
Key features
Write feature with style-matching suggestions for overcoming writer's block
Describe and Expand to turn sparse sentences into vivid sensory prose
Rewrite feature for revising and tightening prose without losing intent
Story Bible for maintaining character, world, and plot consistency across manuscripts
Canvas for visual story planning with outline templates
Chat for asking questions about your story grounded in Story Bible
Feedback feature providing five actionable areas for improvement
Visualize to generate character art from descriptions
Head-to-head comparison of up to 200 variants
Bradley-Terry model ranking with calibrated odds
Honest uncertainty verdicts: Clear, Lean, Too close to call
Brand profiles to calibrate accuracy on your audience
Works for YouTube titles, subject lines, ad headlines, and article headlines
Accuracy measured on 9,841 held-out A/B tests
What makes it different
Proprietary Muse and Ballad AI models trained specifically for fiction
Built by writers for writers who understand storytelling craft
Keeps your unique voice instead of producing generic chatbot prose
Unlimited creative freedom including unfiltered writing of adult scenes
82% accuracy on clear calls, trained on thousands of real A/B tests never seen during tuning
Honest about uncertainty instead of always crowning a winner
56 times cheaper than Claude Sonnet while maintaining comparable accuracy
Custom calibration to your audience's behavior via brand profiles
Compare versions in both orders to cancel out model bias