Real store listing. Store data comes from public listings; the assessment type and evidence coverage are labeled on this page.
Appworthy

AI Baby Generator - TinyFaces

AI Baby Generator app that predicts how a baby's face might look by analyzing…

HEYOS
Review signals only
Get it onGoogle Play
Google Play rating4.5★5.9K ratings
PriceFreeIn-app purchases
Age4+Store age rating
CategoryKids
DeveloperHEYOS

At a glance

Full report

Review signals only — 1 user-reported signal. Review signals, not findings. Nothing here is an assessment.

Review signals 1

From review signals only, 18 Oct 2026.

The store currently lists version 5.2.2, updated 2026-04-30.

Preview

Screenshot 1Screenshot 2Screenshot 3Screenshot 4Screenshot 5Screenshot 6Screenshot 7Screenshot 8

Store screenshots supplied by the developer.

About this app

AI Baby Generator app that predicts how a baby's face might look by analyzing the features of two parent faces! Tinyfaces uses advanced AI models to analyze parents characteristics and predicts your baby's face.

Ever wondered how your future baby might look? Curious about the cute combination of you and your partner’s genes? Or ever thought about what would happen if two celebrities had a baby? With the AI Baby Generator app, your questions are just a tap away from being answered!

This app must be used for entertainment purposes only. The goal of making the app is having a fun with your girlfriend/boyfriend or wife/husband. Please do not take this app seriously!

Privacy Policy: https://heyos.co/privacy-policy

Terms of Use: https://heyos.co/terms-of-use

From the developer’s store description.

For developers and the curious

The full report

The evidence, sources, measurements and versions behind every label above.

Findings and evidence

No findings published
No findings are published for this listing. These are review signals, not findings: nothing here is an assessment.

Review signals 1

Recurring themes across the reviews we scanned. Each links to what reviewers report.

What reviewers report

320 reviews read · 1 review signal

320 reviews scanned. These are signals from public reviews, not findings. Nothing here is an assessment.

Paywall blocks the basics

Review signal, not a finding

7 reviews · 2.2% of reviews scanned

This is the worst I've ever you can only do one thing like this is the worst app ever like you just one thing and then you have to pay for the rest just to make one it might sound like that I'm not making sense but other people agree with…

1★ · Google Play · 2024-06-25

If I could leave 0 stars I would. It's a total scam. It's free to download, pay to actually use. YOU HAVE TO PAY TO USE THE APP. IT IS NOT FREE. total garbage

1★ · Google Play · 2024-04-01

Scam App. Can't do anything without paying

1★ · Google Play · 2024-12-11

A sampled review illustrates one person’s experience. It does not establish a finding on its own.

Measurements

5 measured · 3 not assessed

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.

From store data and reviews

Developer replies to reviews
Replies to fewer than 1 review in 20
Price in the store description
States no price and billing period
Cancelling, in the store description
Does not say how to cancel
Themes reported by reviewers
No theme reported
Counted from the reviews we have read for this app. "No theme reported" means no theme reached our reporting threshold — it is not a finding that nothing is wrong with this app, and we do not say it is.
Five-star share of ratings
65–79% five-star
Arithmetic on the stores' own published rating counts. It says nothing about why the ratings fall where they do.

In the app package we scanned

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.

Sensitive permissions
Not assessed
No package has been scanned for this app
Analytics or tracking SDKs in the scanned package
Not assessed
No package has been scanned for this app
Advertising SDKs in the scanned package
Not assessed
No package has been scanned for this app

Measurement vocabulary 1.4 · how these are measured

Versions and dates analysed

Review signals only

Review signals only. No automated analysis of the app itself has been run, so there is no analysed version to report; the signals were read from public reviews on 18 Oct 2026.

Store update history

Each store’s release notes, as the developer wrote them. They are the developer’s words, not ours.

Google Play

Version 5.2.2 · 2026-04-30

No release notes were provided for this version.

Assessment record

Status
Review signals only
App identifier
ai-baby-generator-google-co-appnation-babygenerator
Review signals scanned
18 Oct 2026
Sources used
User reviews
Reviews read
320
Package examined
No package scan
Measurement vocabulary
1.4
Human inspection
Not completed

Store facts

Google Play

What the stores publish. Store ratings are the stores’ numbers, not Appworthy’s, and are never averaged across stores.

Google Play

Store rating
4.46 ★ · 5,921 ratings
Version
5.2.2
Updated
30 Apr 2026
Price
Free · In-app purchases
Age rating
4+
Size
Not supplied
Open in Google Play
Developer
HEYOS
Category
Kids
Listing price
Free · In-app purchases

Purchases the store lists

 What this app sells
Google Play doesn’t publish per-purchase prices, so this list covers the other store only.

Method and limits

What this report can and cannot show

How a review signal works

A review signal is produced automatically from public app reviews by a classifier — never by a hands-on Appworthy test, and never by a human analyst. It exists so a real, not-yet-audited app can carry more than a blank “Not yet tested” listing, without ever being mistaken for an assessment.

A theme only appears above once at least 5 distinct reviews corroborate it — one angry review can never tag an app. These thresholds are published settings and may be tuned as coverage grows.

It carries no confirmed findings — reviews are one kind of evidence, and nothing here has been hands-on tested. The moment Appworthy publishes a full assessment of this app, it replaces this signal, permanently.

Limits of this report

  • A package scan is static. It identifies code and text in one Android build. It does not measure a live ad session, test a deletion request, or count the steps needed to cancel.
  • Reviews keep their sample. A review-only charge shows distinct reviewers, the share and the sample size, and is published only once it clears that label’s published threshold. Calibration labels are machine-drafted and not yet confirmed by a person.
  • Not assessed is a state. It is never a zero and never a pass.
  • A missing label is not a clean bill of health. It means the evidence did not support one, not that the app is problem-free.
Not yet human-reviewed. A human review replaces this review-derived signal with hands-on, recorded measurements. Hands-on inspections are not yet open.
Review thresholds Read the methodology For developers

Request a correction

[email protected]

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.

Report a factual error — free Email a correction