The avatar looks realistic and holds attention well enough for a mobile-app ad, with speech and lip movements aligned naturally.
What was measured
Avatar realism
How believable the presenter looks and how uncanny or AI-obvious the avatar appears, including lip-sync plausibility.
decisive for this rankingtransformation
This ranking is about whether the avatar convincingly plays the creator in the ad; if it looks uncanny or AI-obvious, the core product has failed. (3 of 3 judges)
What was given, what came back
Test input: Duolingo – Mobile App · text
Input — what we sent
The exact prompt
Product URL: https://www.duolingo.com/ Exact Script Hook: Learning a new language has never been this easy. Script: I've been using Duolingo for a few minutes every day, and it's made language learning simple and fun. The short lessons are easy to follow, and the daily practice keeps me motivated. If you're planning to learn a new language, give Duolingo a try. Output Requirements - Vertical (9:16) - 20–30 seconds - UGC-style AI presenter - Natural AI voice - Captions enabled
A short-form UGC-style video ad prompt for a consumer mobile app, designed to test whether a tool can explain app benefits simply and persuasively in a social ad format.
Why this input is hard
- · mobile app understanding
- · consumer app promotion
- · script quality
- · avatar realism
- · voice quality
- · caption quality
- · overall ad readiness
Output — unretouched
Also checked on this input — same tool, 6 other criteria
Ad-readiness◐ MixedThe workflow produces a quick end-to-end video, but the free-plan watermark and generic app presentation keep it from being fully ad-ready without extra polish.Caption quality✓ WorkedCaptions are correctly generated and synced with the narration.Platform formats✓ WorkedThe generator outputs a short-form vertical video in 9:16 format suitable for TikTok, Reels, and Shorts.Product understanding⚠ StruggledThe output does not clearly showcase the app interface and relies on generic background context, which weakens app-specific product understanding and relatability.Script quality & persuasiveness◐ MixedThe narration is easy to understand and matches Duolingo's simple-learning vibe, but it is not especially energetic and the report notes minor phrasing drift.Voice quality◐ MixedThe voice is simple and clean and fits educational/app promotion content, but the delivery is described as slightly neutral rather than highly engaging.
Provenance
- Observation
- 35a90460-b527-402d-91f7-1b1aca55a68c
- Evidence run
- f91a51ec-b400-46fe-97f5-7e779fe17532
- Study
- Generate UGC-Style Video Ads With AI Avatars
- Research task
- 86baxegpg
- Tested at
- not recorded
- Source
- first-party
- Evidence state
- verified
- Proof shown
- input + output shown
- Cost / latency
- not captured
- Repeat run
- not captured
- Tester
- not captured
The last three rows are honest blanks, not placeholders — our capture has no field for them yet.
Query this
get_evidence({
tool: "creatify-ai"
})MCP · mcp.aidemos.com/api/mcp
Free with attribution.
Same input, same check — 4 other tools
measured on Avatar realism
AKOOL⚠ StruggledThe presenter still reads as AI-generated compared with higher-end tools.Synthesia✓ WorkedThe generated presenter delivered smoothly with maintained lip-sync, so the avatar reads as technically coherent in preview.Topview AI⚠ StruggledThe presenter still looks AI-like, and minor lip-sync mismatches remain visible.Vidnoz AI⚠ StruggledThe presenter still looks AI-generated compared with higher-end tools, so the avatar does not fully pass as a natural human creator.
This evidence is published in
From the same study (page rebuilt from a later run)
Real inputs and real outputs, no retouching · every cell queryable via API & MCP · aidemos.com