For indie app developers
Your app is done.
Now write the store listing.
StoreScribe studies the apps you're up against, then writes your App Store and Google Play listings inside every character limit, with the words your category actually searches for. In English and five more languages, in about two minutes.
That's your whole app name and subtitle. Every word has to earn its place and still read naturally.
Apple's keyword field counts bytes, so Japanese gets about a third of the room. Most tools don't notice.
People in Tokyo don't search with translated English words. Each language gets its own keywords.
How it works
- 1
Tell it about your app
Name, a one-line pitch and a few screenshots. The model reads the screenshots to see what your app really does.
- 2
It researches the category
It pulls the top App Store and Google Play results for your search terms and finds the words they all use.
- 3
It writes, then checks
Gemma 4 drafts each field. Code checks every limit and store rule, and anything that doesn't fit is rewritten until it does.
- 4
You ship it
Edit with live counters, keep every version, export straight to fastlane, then track where you rank, day by day.
Or run it in your repo
Skip the form. Run one command inside your app's project and StoreScribe reads it for you: the app name and bundle ids, the README, the screens in your code, your current store listing and your screenshots. The finished listing lands in fastlane/metadata, ready to upload.
- Works with Flutter, React Native, Expo, Swift and Kotlin projects
- Add
--localto run Gemma on your own machine with Ollama. Nothing leaves your laptop.
~/aerotail $ npx github:sbis04/storescribe --local --langs ja-JP ✓ AeroTail (Flutter, iOS, Android) read 4 files, 6 screens in the code • Reading the project ✓ Pitch: Track aircraft flying near you in real time • Writing the App Store listing ↺ Subtitle is 43/30, tightening it ✓ App Store listing ready ✓ Japanese ready ✓ Done in 81 s · free, ran on this machine ✓ Wrote 16 files to fastlane/metadata
Why an open model
A listing isn't written once. You rewrite it for every update, every season, every new market. That only works as a cheap subscription if each draft costs almost nothing.
- A fraction of a cent per listing. StoreScribe runs Gemma 4, an open-weight model, on DigitalOcean. Six languages for both stores costs less than a cent to generate.
- Your unreleased app stays yours. Screenshots are read and thrown away. You can run the whole thing on your own laptop with Ollama, so nothing leaves your machine.
- No lock-in. The model is one setting. Swap in a bigger open model, or fine-tune one on your best-converting listings.
Pricing
It's free during the beta. Here's the plan after that.
Free
- 1 app
- English + 2 languages
- Live limit checks and fastlane export
Indie
- 5 apps, unlimited drafts
- English + 13 languages
- Competitor research on both stores
- Daily rank tracking
Studio
- Unlimited apps
- Everything in Indie
- Run it on your own server