{"observation":{"id":"7161f9f6-898f-46f1-907c-50a97ff79b05","tool":"invideo-ai","tool_name":"Invideo AI","criterion":"avatar-realism","criterion_name":"Avatar realism","criterion_definition":"Believable presenter; accurate lip-sync; how uncanny or AI-obvious the presenter looks.","criterion_evidence_type":"transformation","criterion_rank_role":"decisive","criterion_rank_role_reason":"If the presenter looks fake or lip-sync is off, the ad fails at the core UGC avatar job. (3 of 3 judges)","scenario":"duolingo-mobile-app","scenario_name":"Duolingo – Mobile App","group_tag":"ugc-style-video-ads","scenario_description":"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.","modality":"mixed","input_text":"Product URL: https://www.duolingo.com/\n\nExact script:\nHook: Learning a new language has never been this easy.\nScript: 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.\n\nOutput requirements:\n- Vertical (9:16)\n- 20–30 seconds\n- UGC-style AI presenter\n- Natural AI voice\n- Captions enabled","input_artifact_refs":[],"stresses":["Mobile app understanding","Consumer app promotion","Script quality","Avatar realism","Voice quality","Caption quality","Overall ad readiness"],"verdict":"worked","score":null,"score_total":null,"note":"The presenter reads as a consistent human avatar with a clean UGC look throughout the clip, with no obvious flicker or identity break reported.","evidence_state":"verified","source":null,"artifacts":[{"url":"https://cdn.futuresmart.ai/public/aidemos/2d708f66a6554c76aa83c81aa49797c7.mp4?v=1","role":"output","alt":null},{"url":"https://cdn.futuresmart.ai/public/aidemos/e48056a702784f44965a5dec6c18e98b.mp4?v=1","role":"output","alt":null}],"run_id":"9fdbb84b-4aa0-484d-8f89-5c46608019a5","study_title":"Generate UGC-Style Video Ads With AI Avatars","study_kind":"generation","research_task":"86baxegpg","tested_at":null,"completeness":"input-and-output","input":{"state":"text","text":"Product URL: https://www.duolingo.com/\n\nExact script:\nHook: Learning a new language has never been this easy.\nScript: 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.\n\nOutput requirements:\n- Vertical (9:16)\n- 20–30 seconds\n- UGC-style AI presenter\n- Natural AI voice\n- Captions enabled","files":[],"modality":"mixed","stresses":["Mobile app understanding","Consumer app promotion","Script quality","Avatar realism","Voice quality","Caption quality","Overall ad readiness"]},"tool_page_slug":"invideo-ai","tool_url":"https://aidemos.com/tools/invideo-ai","permalink":"https://aidemos.com/evidence/7161f9f6-898f-46f1-907c-50a97ff79b05","api_url":"https://ai.aidemos.com/v1/observations/7161f9f6-898f-46f1-907c-50a97ff79b05"},"peers":[{"id":"67d03d68-a3e0-4842-b3fb-3d74eed26da6","tool":"akool","tool_name":"AKOOL","verdict":"mixed","score":null,"score_total":null,"note":"The presenter is serviceable, but the avatar still looks moderately AI-generated rather than high-end realistic.","artifact_count":1,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/ada242395b9642fdacde72d4547aafe9.mp4?v=1","evidence_url":"https://aidemos.com/evidence/67d03d68-a3e0-4842-b3fb-3d74eed26da6"},{"id":"63626937-61a4-48f4-96d2-3e6b79f8a8ba","tool":"dreamface","tool_name":"DreamFace","verdict":"mixed","score":null,"score_total":null,"note":"The Duolingo avatar has good facial realism and natural gestures/weight shifting, but the right hand turns into a smooth mitten-like blob around 0:11.","artifact_count":2,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/326fff910d734e64af5d6b2b3c668b24.mp4?v=1","evidence_url":"https://aidemos.com/evidence/63626937-61a4-48f4-96d2-3e6b79f8a8ba"},{"id":"9012a876-7dac-4276-89c3-aa9dc9ebcf9d","tool":"heygen","tool_name":"HeyGen","verdict":"worked","score":null,"score_total":null,"note":"The Duolingo output reads as a casual creator-style presenter rather than an AI-obvious stock avatar, with the report calling the setting genuinely UGC-authentic.","artifact_count":2,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/e1595503067242cdbfafa0a9676f1a5a.mp4?v=1","evidence_url":"https://aidemos.com/evidence/9012a876-7dac-4276-89c3-aa9dc9ebcf9d"},{"id":"b5bf84f3-e76a-41ce-a229-dbd3528280ed","tool":"joggai","tool_name":"JoggAI","verdict":"worked","score":null,"score_total":null,"note":"Generates a strong-looking photorealistic avatar with no visible artifacts; the report says the face, hair, and teeth look natural even in a wide smile.","artifact_count":2,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/abcbc5e48bb14dc99f8490b2808cf261.mp4?v=1","evidence_url":"https://aidemos.com/evidence/b5bf84f3-e76a-41ce-a229-dbd3528280ed"},{"id":"a822e15b-a091-4f92-8344-d0bf07c19660","tool":"synthesia","tool_name":"Synthesia","verdict":"worked","score":null,"score_total":null,"note":"The Duolingo output used a smooth, centered talking-head avatar, and the report says lip-sync accuracy was maintained.","artifact_count":1,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/ea4c634e3873477ba8e836f199738bcc.mp4?v=1","evidence_url":"https://aidemos.com/evidence/a822e15b-a091-4f92-8344-d0bf07c19660"},{"id":"6a41cd91-74b9-464b-9b3f-6fdefbfccc7b","tool":"topview-ai","tool_name":"Topview AI","verdict":"mixed","score":null,"score_total":null,"note":"The avatar remains visible and moves slightly, but the report describes the presenter as more AI-like than premium tools.","artifact_count":2,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/804557dc8e114b7b881b3057d7014c4f.mp4?v=1","evidence_url":"https://aidemos.com/evidence/6a41cd91-74b9-464b-9b3f-6fdefbfccc7b"},{"id":"489c4461-ad1d-491e-a950-62376aaf9b59","tool":"vidnoz-ai","tool_name":"Vidnoz AI","verdict":"mixed","score":null,"score_total":null,"note":"Produces a believable talking-head presenter, but the report still describes the avatar as moderately AI-generated compared with higher-end tools.","artifact_count":1,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/f25b8326c2154e5688b7d75b8d2dc085.mp4?v=1","evidence_url":"https://aidemos.com/evidence/489c4461-ad1d-491e-a950-62376aaf9b59"}],"other_criteria":[{"id":"9493dd01-fa8e-41e2-879b-0214836a5a08","criterion":"ad-readiness","criterion_name":"Ad-readiness","rank_role":"decisive","verdict":"mixed","score":null,"score_total":null,"note":"The clip is branded and complete, but the generic b-roll and non-clickable end card make it less action-ready as a paid ad without another review pass.","artifact_count":3,"evidence_url":"https://aidemos.com/evidence/9493dd01-fa8e-41e2-879b-0214836a5a08"},{"id":"107f3ac0-9c11-45b0-aa76-f6d22bddced6","criterion":"b-roll-product-integration","criterion_name":"B-roll / product integration","rank_role":"decisive","verdict":"mixed","score":null,"score_total":null,"note":"The clip adds a timed phone-and-coffee cutaway, but the screen content is blurred and generic instead of product-specific, so the supporting footage does not fully reinforce the app.","artifact_count":3,"evidence_url":"https://aidemos.com/evidence/107f3ac0-9c11-45b0-aa76-f6d22bddced6"},{"id":"4db20ba1-6e74-4050-9a0d-363b7b367453","criterion":"caption-quality","criterion_name":"Caption quality","rank_role":"decisive","verdict":"mixed","score":null,"score_total":null,"note":"The captions visibly advance across the clip and support the CTA line, but the report does not separately validate timing or styling beyond the sampled frame progression.","artifact_count":2,"evidence_url":"https://aidemos.com/evidence/4db20ba1-6e74-4050-9a0d-363b7b367453"},{"id":"7a6225f6-e4ba-40b5-b2f7-b5ee9a7ca9ba","criterion":"product-understanding","criterion_name":"Product understanding","rank_role":"decisive","verdict":"mixed","score":null,"score_total":null,"note":"The output gets the brand right in the outro card, but the mid-script phone b-roll is generic message-bubble UI rather than an actual Duolingo lesson screen, so product specificity is only partial.","artifact_count":4,"evidence_url":"https://aidemos.com/evidence/7a6225f6-e4ba-40b5-b2f7-b5ee9a7ca9ba"},{"id":"8af2d396-37c8-4209-83b4-31ab2c9fbea0","criterion":"script-quality-persuasiveness","criterion_name":"Script quality & persuasiveness","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"The script is reproduced verbatim and reaches the closing CTA line without truncation, so the testimonial structure and call-to-action remain intact.","artifact_count":2,"evidence_url":"https://aidemos.com/evidence/8af2d396-37c8-4209-83b4-31ab2c9fbea0"}],"appears_in":[{"page_type":"ranking","slug":"ugc-video-ad-generators","title":"Best AI Tools for Generating UGC-Style Video Ads With AI Avatars","url":"https://aidemos.com/best/ugc-video-ad-generators","binding":"run"}],"same_scenario":[{"id":"67d03d68-a3e0-4842-b3fb-3d74eed26da6","tool":"akool","tool_name":"AKOOL","verdict":"mixed","score":null,"score_total":null,"note":"The presenter is serviceable, but the avatar still looks moderately AI-generated rather than high-end realistic."},{"id":"63626937-61a4-48f4-96d2-3e6b79f8a8ba","tool":"dreamface","tool_name":"DreamFace","verdict":"mixed","score":null,"score_total":null,"note":"The Duolingo avatar has good facial realism and natural gestures/weight shifting, but the right hand turns into a smooth mitten-like blob around 0:11."},{"id":"9012a876-7dac-4276-89c3-aa9dc9ebcf9d","tool":"heygen","tool_name":"HeyGen","verdict":"worked","score":null,"score_total":null,"note":"The Duolingo output reads as a casual creator-style presenter rather than an AI-obvious stock avatar, with the report calling the setting genuinely UGC-authentic."},{"id":"b5bf84f3-e76a-41ce-a229-dbd3528280ed","tool":"joggai","tool_name":"JoggAI","verdict":"worked","score":null,"score_total":null,"note":"Generates a strong-looking photorealistic avatar with no visible artifacts; the report says the face, hair, and teeth look natural even in a wide smile."},{"id":"a822e15b-a091-4f92-8344-d0bf07c19660","tool":"synthesia","tool_name":"Synthesia","verdict":"worked","score":null,"score_total":null,"note":"The Duolingo output used a smooth, centered talking-head avatar, and the report says lip-sync accuracy was maintained."},{"id":"6a41cd91-74b9-464b-9b3f-6fdefbfccc7b","tool":"topview-ai","tool_name":"Topview AI","verdict":"mixed","score":null,"score_total":null,"note":"The avatar remains visible and moves slightly, but the report describes the presenter as more AI-like than premium tools."},{"id":"489c4461-ad1d-491e-a950-62376aaf9b59","tool":"vidnoz-ai","tool_name":"Vidnoz AI","verdict":"mixed","score":null,"score_total":null,"note":"Produces a believable talking-head presenter, but the report still describes the avatar as moderately AI-generated compared with higher-end tools."}]}