{"observation":{"id":"8ff9b798-baad-4160-8b98-7a90b05a1ca0","tool":"heygen","tool_name":"Heygen","criterion":"long-form-consistency","criterion_name":"Long-Form Consistency","criterion_definition":"Whether voice quality, pacing, and pronunciation stay consistent over longer passages instead of degrading after a few sentences.","criterion_evidence_type":"transformation","criterion_rank_role":"decisive","criterion_rank_role_reason":"For text-to-voiceover work, the voice must stay stable across longer scripts; degradation means the output is not reliable. (3 of 3 judges)","scenario":"high-quality-voice-sample","scenario_name":"High-Quality Voice Sample","group_tag":"voice-cloning","scenario_description":"A clean studio-quality voice recording without background noise, used to test the best-case ceiling for voice cloning, pronunciation stability, and naturalness.","modality":"mixed","input_text":"Removing objects from videos used to take hours of manual editing. Now AI tools claim to do it in minutes. So we tested five AI video object removers to find the most reliable one. We used the same three inputs across all the tools for a fair comparison. ABC Labs showed unstable tracking and heavy distortion. Media.io offered fast processing but unusable outputs. PhotoRoom mostly relied on blur masking instead of real reconstruction. Runway delivered the cleanest removals with the most stable tracking and realistic scene reconstruction. Here's exactly how we tested it.","input_artifact_refs":[{"alt":null,"url":"https://d3epheqghktydj.cloudfront.net/research-media-heygen-input-high-quality-884aedc4e603.wav","role":"input","filename":"heygen-input-high-quality.wav"}],"stresses":["Maximum voice-cloning accuracy","Naturalness with optimal source quality","Long-form consistency","Pronunciation stability","Voice preservation under ideal conditions"],"verdict":"struggled","score":null,"score_total":null,"note":"The longer-script high-quality generation had flow interruptions, word mispronunciations, inconsistent delivery, and the report says multiple regenerations may be required for production-ready results.","evidence_state":"verified","source":null,"artifacts":[{"url":"https://d3epheqghktydj.cloudfront.net/research-media-heygen-output-high-quality-variant-3-bes-3b44d7550666.wav","role":"output","alt":null}],"run_id":"46222c41-0046-41cc-bfaa-5f7ba6aa4933","study_title":"Clone Your Voice and Generate Voiceover from Text","study_kind":"generation","research_task":"86ba42bx1","tested_at":null,"completeness":"input-and-output","input":{"state":"text-and-files","text":"Removing objects from videos used to take hours of manual editing. Now AI tools claim to do it in minutes. So we tested five AI video object removers to find the most reliable one. We used the same three inputs across all the tools for a fair comparison. ABC Labs showed unstable tracking and heavy distortion. Media.io offered fast processing but unusable outputs. PhotoRoom mostly relied on blur masking instead of real reconstruction. Runway delivered the cleanest removals with the most stable tracking and realistic scene reconstruction. Here's exactly how we tested it.","files":[{"url":"https://d3epheqghktydj.cloudfront.net/research-media-heygen-input-high-quality-884aedc4e603.wav","filename":"heygen-input-high-quality.wav","alt":"High-Quality Voice Sample","role":"input"}],"modality":"mixed","stresses":["Maximum voice-cloning accuracy","Naturalness with optimal source quality","Long-form consistency","Pronunciation stability","Voice preservation under ideal conditions"]},"tool_page_slug":"heygen","tool_url":"https://aidemos.com/tools/heygen","permalink":"https://aidemos.com/evidence/8ff9b798-baad-4160-8b98-7a90b05a1ca0","api_url":"https://ai.aidemos.com/v1/observations/8ff9b798-baad-4160-8b98-7a90b05a1ca0"},"peers":[{"id":"44e04da3-764d-4c4f-9b78-58fbdcfe7fd9","tool":"elevenlabs","tool_name":"ElevenLabs","verdict":"worked","score":null,"score_total":null,"note":"Keeps voice stability across extended scripts and is described as good for long-form narration, with no reported degradation over longer passages.","artifact_count":3,"thumbnail":"https://d3epheqghktydj.cloudfront.net/research-media-elevenlabs-highquality-input-4dac94a57d04.wav","evidence_url":"https://aidemos.com/evidence/44e04da3-764d-4c4f-9b78-58fbdcfe7fd9"},{"id":"ff632063-0449-48b6-b605-f9c7176feabe","tool":"inworld","tool_name":"Inworld","verdict":"struggled","score":null,"score_total":null,"note":"In the ~1:04 high-quality output, matching accuracy degraded further as the clip progressed, so consistency weakened over the longer passage.","artifact_count":2,"thumbnail":"https://d3epheqghktydj.cloudfront.net/research-media-inworld-highquality-input-5a7af892998c.wav","evidence_url":"https://aidemos.com/evidence/ff632063-0449-48b6-b605-f9c7176feabe"},{"id":"c62a8366-7e61-4481-89d2-713802e118f4","tool":"minimax","tool_name":"MiniMax","verdict":"worked","score":null,"score_total":null,"note":"The complete ~19-second output held up fine at that length, with no visible degradation reported within the generated clip.","artifact_count":1,"thumbnail":"https://d3epheqghktydj.cloudfront.net/research-media-minimax-output-high-quality-64a65a87ed76.mp3","evidence_url":"https://aidemos.com/evidence/c62a8366-7e61-4481-89d2-713802e118f4"},{"id":"eedd48b7-de42-4024-a225-dfe870fd6e87","tool":"topmediai-voice-cloning","tool_name":"TopMediai Voice Cloning","verdict":"worked","score":null,"score_total":null,"note":"Gen remains consistent through the generated narration on the clean sample, with no interruptions or instability observed.","artifact_count":2,"thumbnail":"https://d3epheqghktydj.cloudfront.net/research-media-topmediai-highquality-input-6c26a9323e7b.wav","evidence_url":"https://aidemos.com/evidence/eedd48b7-de42-4024-a225-dfe870fd6e87"},{"id":"11bf336a-1887-480d-afb6-b231fbc3d21c","tool":"uberduck","tool_name":"Uberduck","verdict":"worked","score":null,"score_total":null,"note":"The output stayed poor throughout the passage rather than degrading over length, so no later-stage dropoff was observed.","artifact_count":2,"thumbnail":"https://d3epheqghktydj.cloudfront.net/research-media-high-quality-input-recording-f326629d7802.mp4","evidence_url":"https://aidemos.com/evidence/11bf336a-1887-480d-afb6-b231fbc3d21c"},{"id":"2ae4e858-ea5a-4e0e-816a-197ac880c680","tool":"vocalai","tool_name":"VocalAI","verdict":"worked","score":null,"score_total":null,"note":"Consistency was maintained throughout the script, though the speech still ran faster than expected.","artifact_count":1,"thumbnail":"https://d3epheqghktydj.cloudfront.net/research-media-vocalai-output-high-quality-1583ecfff017.wav","evidence_url":"https://aidemos.com/evidence/2ae4e858-ea5a-4e0e-816a-197ac880c680"}],"other_criteria":[{"id":"3e841b26-1213-464f-a700-cbcad3e2d9d4","criterion":"naturalness","criterion_name":"Naturalness & Human Quality","rank_role":"decisive","verdict":"mixed","score":null,"score_total":null,"note":"The first high-quality clone was around 80% human-like, but it still retained synthetic characteristics.","artifact_count":2,"evidence_url":"https://aidemos.com/evidence/3e841b26-1213-464f-a700-cbcad3e2d9d4"},{"id":"c208f7da-4963-4cfc-a24d-dc6532da9051","criterion":"voice-match-accuracy","criterion_name":"Voice Match Accuracy","rank_role":"decisive","verdict":"struggled","score":null,"score_total":null,"note":"The second high-quality clone showed lower accuracy because of a noticeable vocal shift and was described as sounding closer to a female voice profile.","artifact_count":1,"evidence_url":"https://aidemos.com/evidence/c208f7da-4963-4cfc-a24d-dc6532da9051"},{"id":"26db4b2a-85a8-4bc5-a1e2-4211467cc2ca","criterion":"voice-match-accuracy","criterion_name":"Voice Match Accuracy","rank_role":"decisive","verdict":"mixed","score":null,"score_total":null,"note":"The first high-quality clone achieved only moderate similarity to the original voice, so it was usable but not a strong identity match.","artifact_count":1,"evidence_url":"https://aidemos.com/evidence/26db4b2a-85a8-4bc5-a1e2-4211467cc2ca"},{"id":"27d76bf7-8e01-4067-ab1a-0aaa49bec331","criterion":"voice-match-accuracy","criterion_name":"Voice Match Accuracy","rank_role":"decisive","verdict":"mixed","score":null,"score_total":null,"note":"The best high-quality clone still reached only about 70% similarity to the original voice, so it remained below a strong match despite being the best of the three.","artifact_count":2,"evidence_url":"https://aidemos.com/evidence/27d76bf7-8e01-4067-ab1a-0aaa49bec331"}],"appears_in":[{"page_type":"ranking","slug":"voice-cloning-tools","title":"Best AI Tools to Clone Your Voice and Generate Voiceovers from Text","url":"https://aidemos.com/best/voice-cloning-tools","binding":"run"}],"same_scenario":[{"id":"44e04da3-764d-4c4f-9b78-58fbdcfe7fd9","tool":"elevenlabs","tool_name":"ElevenLabs","verdict":"worked","score":null,"score_total":null,"note":"Keeps voice stability across extended scripts and is described as good for long-form narration, with no reported degradation over longer passages."},{"id":"ff632063-0449-48b6-b605-f9c7176feabe","tool":"inworld","tool_name":"Inworld","verdict":"struggled","score":null,"score_total":null,"note":"In the ~1:04 high-quality output, matching accuracy degraded further as the clip progressed, so consistency weakened over the longer passage."},{"id":"c62a8366-7e61-4481-89d2-713802e118f4","tool":"minimax","tool_name":"MiniMax","verdict":"worked","score":null,"score_total":null,"note":"The complete ~19-second output held up fine at that length, with no visible degradation reported within the generated clip."},{"id":"eedd48b7-de42-4024-a225-dfe870fd6e87","tool":"topmediai-voice-cloning","tool_name":"TopMediai Voice Cloning","verdict":"worked","score":null,"score_total":null,"note":"Gen remains consistent through the generated narration on the clean sample, with no interruptions or instability observed."},{"id":"11bf336a-1887-480d-afb6-b231fbc3d21c","tool":"uberduck","tool_name":"Uberduck","verdict":"worked","score":null,"score_total":null,"note":"The output stayed poor throughout the passage rather than degrading over length, so no later-stage dropoff was observed."},{"id":"2ae4e858-ea5a-4e0e-816a-197ac880c680","tool":"vocalai","tool_name":"VocalAI","verdict":"worked","score":null,"score_total":null,"note":"Consistency was maintained throughout the script, though the speech still ran faster than expected."}]}