The Duolingo output was generated in landscape rather than the requested vertical 9:16 short-form format.
What was measured
Platform formats
Correct aspect ratios and lengths for each channel or short-form platform.
context, not decisivetransformation
Aspect ratios and length presets are delivery convenience; they matter, but they do not by themselves make the ad better or worse. (3 of 3 judges)
What was given, what came back
Test input: Duolingo – Mobile App · mixed · group: ugc-style-video-ads
Input — what we sent
Input, verbatim
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 promo prompt for a consumer mobile app, designed to test whether the tool can explain app benefits simply and persuasively while generating a realistic AI-presenter video.
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, 4 other criteria
Ad-readiness✗ FailedThe Duolingo ad was not runnable as-is because downloading required an upgraded plan and the output stayed landscape instead of vertical.Avatar realism✓ WorkedThe Duolingo output used a smooth, centered talking-head avatar, and the report says lip-sync accuracy was maintained.Script quality & persuasiveness◐ MixedThe Duolingo script explained the app benefits clearly, but the report says the presentation felt less engaging for UGC ads and had limited emotional expressiveness.Voice quality✓ WorkedThe Duolingo voice was reported as clear and well-paced, with no technical issues during generation.
Provenance
- Observation
- f410dd67-fcba-4ee3-ac8e-1336e9dd7204
- Evidence run
- 9fdbb84b-4aa0-484d-8f89-5c46608019a5
- 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: "synthesia",
scenario: "ugc-style-video-ads"
})MCP · mcp.aidemos.com/api/mcp
Free with attribution.
Same input, same check — 2 other tools
measured on Platform formats
This evidence is published in
Real inputs and real outputs, no retouching · every cell queryable via API & MCP · aidemos.com