Nothing published. That is not a guarantee the app is problem-free.
No specific positive published.
From our automated analysis, 18 Oct 2026.
This analysis describes version 2.0.4 of the app, analyzed 2026-10-18 . The app may have changed since.
The store currently lists version 2.0.4, updated 2026-08-25.
Store screenshots supplied by the developer.
Ready to enter the AI world? Spellai is a user-friendly app that effortlessly turns your words into captivating photos and drawings. With its AI Chat feature, you can enjoy engaging conversations and have your AI friends generate stunning images on the spot. Prepare to be amazed by the breathtaking image quality!
- Create Images While Chatting
Your conversations are no longer just text! Chat with your AI friends, describe a scene, a character, or even a mood, and watch as the app instantly transforms your words into stunning, high-quality images. Whether it’s a dreamy illustration, a vibrant portrait, or a custom wallpaper, your imagination is the only limit. Make every chat a creative adventure!
- Text to AI Art
With our powerful AI editor, you can quickly and easily transform your text into unique photos, from anime-inspired drawings to lifelike photos.…
From the developer’s store description.
For developers and the curious
The evidence, sources, measurements and versions behind every label above.
Open observations that have not cleared the evidence bar.
Misleading advertising: raised by 6 distinct reviewers (1.8% of 333 reviews scanned)
This observation has not cleared the required evidence standard.
Reviewers repeatedly report that the app is not what its advertising showed. We never see the ad creative itself, so nothing we collect can corroborate or refute this — it is published as an attributed user report: what reviewers say, and how many of them said it.
Nothing was published as a thing to watch for in this assessment. That is not a finding that nothing is wrong with the app.
333 reviews read for this analysis. Each observation keeps the sample and store it was based on.
Don’t bother, it will not even create the prompts that it offers. Everything gets rejected. — Like a lot of these apps, you get excited when you see all the prompts they have thinking oh that would be a great one and then one after…
Started off great, but quality is declining; misleading promotion — At first, this seemed to be the most accurate AI creator I’d seen. But over the last month, I’ve noticed a decline in the quality. The ai clips are becoming too…
Fake advertisement. — I downloaded the app because I saw a few ads that claimed the app had absolutely no filters. But it does and there doesn’t seem to be any way of disabling them.
A sampled review illustrates one person’s experience. It does not establish a finding on its own.
Supporting measurements. They are not a complete list of possible harms or positives. “Not assessed” means we could not measure it — never zero, never a pass.
No package has been scanned for this app, so nothing is published about what it ships. That is an absence of evidence, not a finding.
Measurement vocabulary 1.4 · how these are measured
This analysis describes version 2.0.4 of the app, analyzed 2026-10-18 . The app may have changed since.
The store currently lists version 2.0.4, updated 2026-08-25.
Each store’s release notes, as the developer wrote them. They are the developer’s words, not ours.
- Two new advanced AI chat models. - Chat Fix feature: Repair replies in your conversation. - Chat Memory Feature: Better context memory for smoother conversations. - Chat Persona Feature: Customize your own chat personality. - Bug Fixes & Interface Optimizations. If you have any questions, contact us at: [email protected]
Appworthy
spellai-apple-6446022340Assessed 2026-10-18 from 333 user reviews, the store listing and its privacy label. We have not scanned the app's package, so nothing on this page was read from inside the app itself.
What the stores publish. Store ratings are the stores’ numbers, not Appworthy’s, and are never averaged across stores.
No itemized purchase list is available for this listing.
This assessment is produced automatically. Three independent signals are read — user reviews, the store listing and the store privacy disclosure — and each candidate finding is filed under the sources that support it.
No charge stands on one kind of evidence — with one published exception. A finding is either a measured fact that anyone can reproduce (an ad SDK is in the package; every subscription bills weekly; the privacy label omits a tracker we can see), or it is an interpretation — and an interpretation needs independent sources to agree before it reaches the catch list. The exception is a harm only users can see: a charge may publish from reviews alone, as “Reported by N users”, once enough reviewers raise it to clear that charge’s own published bar. That agreement rule is what replaced the human reviewer, not a model’s confidence.
There is no overall score, on purpose. A 0–99 number was published here until 2026-09-15. It was withdrawn because it discriminated too weakly to be the instrument — 44.7% of every pair of apps tied — and because a single number is a verdict where a count is an observation. What publishes instead is a row of measurements, each of which says what was counted and, where we could not look, says that instead.
Findings under One source only are real reports we do not stand behind as findings. They are shown because withholding them entirely would hide a genuine complaint, and labelled because publishing them as charges would be an accusation off a single source.
Write to [email protected], or use the form. Name the finding, the app version and the evidence that needs correcting. Factual corrections are free and never depend on buying anything.