{"schema":"kovapi.model-page/1","model":"minimax-h3-lite","family":["minimax-h3","minimax-h3-lite"],"name":"MiniMax H3 Lite","page":"https://kovapi.com/ja/model/minimax-h3-lite","markdown":"https://kovapi.com/ja/model/minimax-h3-lite.md","docs":"https://kovapi.com/ja/docs/minimax-h3","updated":"2026-11-12","endpoint":{"submit":"POST https://kovapi.com/v1/videos/generations","poll":"GET https://kovapi.com/v1/videos/jobs/{id}","async":true,"submit_status":202,"result":"data[0].url"},"params":{"model":{"type":"string","enum":["minimax-h3","minimax-h3-lite"]},"prompt":{"type":"string","max_chars":5000},"duration":{"type":"integer","min":4,"max":15,"unit":"second","alias":"seconds"},"resolution":{"type":"string","enum":["480P","768P","1080P"],"default":"1080P"},"size":{"type":"string","enum":["16:9","9:16","1:1","4:3","3:4","3:2","2:3","21:9"],"alias":"aspect_ratio"},"images":{"type":"array","items":"https URL","max":9},"image_role":{"type":"string","enum":["first_frame","reference"]},"video_references":{"type":"array","items":{"url":"https URL","duration":"read from the file"},"max":3,"total_seconds_max":15,"billed":true},"audio_reference":{"type":"array","items":"https URL","max":3,"billed":false},"callback_url":{"type":"string","note":"webhook when the job ends"}},"modes":[{"mode":"t2v","title":"テキストから動画","send":"prompt と生成の設定だけ。","get":"テキストから映像と音を生成します。セリフ、効果音、音楽はプロンプトに書きます。","limits":"4〜15 秒の任意の整数秒。resolution を省くと 768P。"},{"mode":"multi_ref","title":"参照画像","send":"images に画像を 1〜5 枚。","get":"画像に写った人物・商品・場所が新しいショットの中に登場します。最初のフレームにはなりません。","limits":"最大 5 枚。image_role: first_frame は拒否されます。"}],"pricing":{"currency":"USD","unit":"second","tiers":{"480P":{"usd_per_second":"$0.015","second_usd_per_second":"$0.005"},"768P":{"usd_per_second":"$0.025","official_usd_per_second":"$0.08","save":"68%","second_usd_per_second":"$0.0125"},"1080P":{"usd_per_second":"$0.036"}},"billed_seconds":"output seconds + reference-video seconds","notes":["1 本の料金 = 選んだ解像度の秒単価 ×（出力の秒数 + 参照動画の秒数）。参照画像と参照音声は無料です。参照動画付きの料金は、「料金計算」の「参照動画」をドラッグすると計算できます。","MiniMax 公式の価格表では H3 は 768P と 2K だけなので、公式価格と並べて比べられるのは 768P だけです。","送信時に料金を仮押さえし、成功すれば同じ金額で確定します。失敗したジョブは全額返金します。大量の試作をさらに安く済ませたいなら MiniMax H3 Lite をご覧ください。"],"second_model":"minimax-h3-lite"},"retention_days":7,"limits":["Lite には最初のフレームも、最初と最後のフレームもありません。画像は常に参照として扱い、image_role: first_frame はその場で拒否され、課金されません。特定の画像から動画を始めたいときは標準版を使ってください。","Lite は参照動画も参照音声も受け付けません。どちらかを付けたリクエストは拒否され、課金されません。これらを使うなら標準版をお使いください。","解像度は 480P と 768P だけです。1080P は拒否され、720P は 768P として扱います。どの動画にも音声が付くので、音楽が不要ならプロンプトに non_diegetic_music: N/A と書いてください。"],"examples":[{"id":"kv-bakery","title":"2 ショット：パン屋の朝いちばんの焼き上がり","mode":"t2v","source":"kovapi","official_no":null,"params":{"duration":8,"resolution":"1080P","size":"16:9"},"cost":"$0.288","video":"https://img.kovapi.com/i/mp-c9751f98f2f98ea8114fa1f3.mp4","poster":"https://img.kovapi.com/i/mp-bd386e68dddf5799b5aecf02.webp","prompt":"integrated_multimodal_description: [Shot 1] Live-action, cinematic, a medium-wide shot frames a baker opening the shutters of a small street bakery before sunrise. The camera pushes in with small amplitude at slow speed as the middle-aged baker with a calm, slightly raspy voice (S1) places a fresh loaf on the wooden counter and says: <d>[English] First batch of the morning.</d> [Shot 2] At 00:05.000, the camera cuts to a close-up of steam rising from the sliced bread while the baker's final words carry over from the previous shot.\n\noverall_soundscape: Wooden shutters scrape open over a quiet street as trays clink softly inside the bakery. The doorbell rings once, followed by light footsteps and the crisp sound of bread being sliced.\n\nnon_diegetic_music: A soft acoustic-guitar pattern at a moderate tempo, joined by sparse upright-bass notes and a gentle fade at the end.","inputs":{"images":[],"video_references":[],"audio_reference":[]}},{"id":"kv-bridge","title":"ブリッジから見る超空間ジャンプ","mode":"t2v","source":"kovapi","official_no":null,"params":{"duration":8,"resolution":"1080P","size":"16:9"},"cost":"$0.288","video":"https://img.kovapi.com/i/mp-66d0f99896d2e402c3af40c3.mp4","poster":"https://img.kovapi.com/i/mp-f6de6baec55fb2d2321e1db1.webp","prompt":"integrated_multimodal_description: [Shot 1] Cinematic, medium wide shot, pushing in slowly. In the cavernous, dimly lit bridge of a starship, sleek metallic consoles with glowing amber displays flank a massive, curved observation window. A female captain, in her late 40s with an athletic build and short silver-streaked black hair, stands in the center midground. She wears a structured, high-collared dark navy military tunic with silver chest insignias. Her back is to the camera, silhouetted against the cool, ambient starlight pouring through the thick glass. She stands perfectly still with her hands clasped tightly behind her back. Outside the window, a massive armada of jagged, dark grey dreadnoughts hovers in tight formation against a deep purple space nebula. The fleet's massive rear thrusters begin to glow with an intense, escalating bright blue light. [Shot 2] At 00:04.500, the camera cuts to a close-up of the captain's face and shakes strongly. The brilliant blue-white light from the fleet's gathering energy reflects vividly in her dark eyes. Suddenly, a blinding white flash floods through the window, completely washing out the background as the fleet jumps to hyperspace. The sheer spatial force violently jolts the bridge, causing the captain from Shot 1 to stagger slightly forward, her shoulders tensing as she visibly braces herself against the physical tremors. As the intense white light fades abruptly, leaving only the dim, empty expanse of the purple nebula reflected on her starkly lit skin, her jaw clenches, and she slowly closes her eyes in the newly emptied space.\noverall_soundscape: A low, resonant hum of the ship's ambient life support systems serves as the baseline, soon drowned out by an audible, escalating, high-pitched electronic whine as the fleet outside charges its hyperdrives. A massive, deafening, bass-heavy boom and sharp crackle erupts during the blinding flash, accompanied by the loud metallic creaking, rattling, and deep thuds of the bridge's bulkheads vibrating under immense physical stress. The intense roaring impact then cuts abruptly back to a hollow, echoing room tone, leaving only the faint, steady hum of the isolated bridge.\nnon_diegetic_music: Cinematic space-opera orchestral score, slow tempo, featuring a solitary, mournful French horn melody over deep, sustained string dissonances that build rapidly in volume and intensity, swelling to a massive orchestral peak before snapping immediately into silence right after the jump.","inputs":{"images":[],"video_references":[],"audio_reference":[]}},{"id":"kv-neon","title":"中国語のセリフとネオンサイン","mode":"t2v","source":"kovapi","official_no":null,"params":{"duration":6,"resolution":"768P","size":"9:16"},"cost":"$0.15","video":"https://img.kovapi.com/i/mp-3ea471e559f9efb09edaf873.mp4","poster":"https://img.kovapi.com/i/mp-f4b78aacfba8f1cd288e6605.webp","prompt":"integrated_multimodal_description: [Shot 1] Live-action, cinematic, a vertical medium shot of a small street-food stall in a narrow old alley at night. A red neon sign reading \"营业中\" glows above the stall and steam rises from a wok. The middle-aged cook with a warm, slightly hoarse voice (S1) tosses noodles in the wok as flames flare up, then looks at the camera and says: <d>[Chinese] 刚出锅的，趁热吃！</d> The camera pushes in with small amplitude at slow speed toward the wok. No subtitles or captions appear on screen.\n\noverall_soundscape: Oil sizzles and the wok clangs against the burner while distant scooters and chatter fill the alley.\n\nnon_diegetic_music: N/A","inputs":{"images":[],"video_references":[],"audio_reference":[]}},{"id":"kv-train","title":"最初のフレーム：雨の列車と手紙","mode":"first_frame","source":"kovapi","official_no":null,"params":{"duration":6,"resolution":"1080P","size":"16:9","image_role":"first_frame"},"cost":"$0.216","video":"https://img.kovapi.com/i/mp-94892704d80349abfc4bbf4e.mp4","poster":"https://img.kovapi.com/i/mp-6f61287a735eb5805007cbd2.webp","prompt":"For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.\n\nintegrated_multimodal_description: [Shot 1] Live-action, cinematic, the young woman shown in <Picture 1> remains beside the rain-covered train window, preserving her appearance, clothing, seat position, and the carriage layout. The camera trucks right with small amplitude at slow speed as she lifts her gaze from the folded letter toward the passing city lights. Her reflection moves across the glass while the quiet, breathy young woman (S1) says: <d>[English] I get off at the next station.</d> She folds the letter along its existing crease.\n\noverall_soundscape: The train wheels produce a steady metallic rhythm beneath a low ventilation hum. Rain ticks against the window while paper rustles softly in her hands.\n\nnon_diegetic_music: Sustained cello notes at a slow tempo with widely spaced piano tones, gradually decreasing in volume.","inputs":{"images":["https://img.kovapi.com/i/mp-71b5ed84bb210183de898f1c.jpg"],"video_references":[],"audio_reference":[]}},{"id":"kv-umbrella","title":"最初と最後のフレーム：雨の中で傘を開く","mode":"first_last","source":"kovapi","official_no":null,"params":{"duration":8,"resolution":"1080P","size":"16:9","image_role":"first_frame"},"cost":"$0.288","video":"https://img.kovapi.com/i/mp-227363d4eedb3bf23a3a199f.mp4","poster":"https://img.kovapi.com/i/mp-48e55aa5ff358fd7b7cf5e16.webp","prompt":"How the reference pictures align with the target video — Picture 1 (from Shot 1) aligns with the 0.00-second mark of the target video; Picture 2 (from Shot 1) aligns with the 8.00-second mark of the target video.\n\nintegrated_multimodal_description: [Shot 1] Live-action, cinematic, a rain-soaked cyclist begins in the position and framing established by Picture 1, holding a closed black umbrella beside a silver bicycle. The camera pulls out with small amplitude at slow speed as she releases the bicycle handle, raises the umbrella above her shoulder, and presses the runner upward until the canopy opens. Water rolls from the expanding fabric while she steps beneath it, rotates the handle into the final angle, and settles into the pose, spacing, and composition established by Picture 2 at the end of the shot.\n\noverall_soundscape: Rain falls steadily on the pavement, followed by the metallic click of the umbrella runner and the soft snap of the canopy opening. Water drips from the bicycle frame as distant traffic passes.\n\nnon_diegetic_music: N/A","inputs":{"images":["https://img.kovapi.com/i/mp-a560b1808c395d8022f926de.jpg","https://img.kovapi.com/i/mp-c32b3d1c8f0211a33cc0047c.jpg"],"video_references":[],"audio_reference":[]}},{"id":"kv-eyewear","title":"参照画像：縦型のアイウェア広告","mode":"multi_ref","source":"kovapi","official_no":null,"params":{"duration":8,"resolution":"1080P","size":"9:16","image_role":"reference"},"cost":"$0.288","video":"https://img.kovapi.com/i/mp-6a00ea489194c7c6e685fcf7.mp4","poster":"https://img.kovapi.com/i/mp-f4eba51dd333ef7fb208e159.webp","prompt":"subject_definitions:\n<Subject 1> is the two female fashion models in <Picture 1>, with slicked-back dark hair, one in a black asymmetric blazer with black-and-silver trousers, the other in a black leather crop top and a long silver satin skirt.\n<Subject 2> is the facial detail of the same two models in <Picture 2>, defining their features and cool expressions.\n<Subject 3> is the futuristic silver sunglasses in <Picture 3>, with wrap-around curves, a sharp cat-eye and goggle hybrid silhouette, mirrored lenses and thin streamlined temples.\n\nsummary:\n[reference generation] A 9:16 high-fashion eyewear commercial on a minimal white cyc: <Subject 1>, with the faces of <Subject 2>, wear <Subject 3> and walk toward the camera with runway attitude, ending on a close-up of the sunglasses on one model's face.\n\nretention_analysis:\n<Subject 1> (appears in [Shot 1]): fully_preserved - the two models' outfits and slicked-back hair are retained.\n<Subject 2> (appears in [Shot 1], [Shot 2]): fully_preserved - their facial features are retained.\n<Subject 3> (appears in [Shot 1], [Shot 2]): fully_preserved - the wrap-around silver frame and mirrored lenses are retained.\n\ndetailed_description:\nThe target video is a clean, high-fashion commercial with soft, even studio light on a seamless white cyc.\n[Shot 1] A vertical full-body shot: both models of <Subject 1>, each wearing a pair of <Subject 3>, walk side by side toward the camera with a confident runway stride and cool demeanor, their faces matching <Subject 2>. The camera pulls out with small amplitude at slow speed.\n[Shot 2] At 00:04.000, the camera cuts to a close-up of the left model's face as she turns her head slightly; the mirrored lenses of <Subject 3> reflect the white studio, and the camera pushes in with small amplitude at slow speed toward the curved silver frame.\n\noverall_soundscape:\nCrisp heel clicks on the studio floor, then a soft whoosh as she turns her head.\n\nnon_diegetic_music:\nA minimal electronic beat at a moderate tempo with deep synth bass, ending on a single sustained chord.","inputs":{"images":["https://img.kovapi.com/i/mp-c542946f4a47ea07d3225571.jpg","https://img.kovapi.com/i/mp-dfa785dd4d3f560bb3eb9492.jpg","https://img.kovapi.com/i/mp-802c1b4d4b5ba8f59682ec61.jpg"],"video_references":[],"audio_reference":[]}},{"id":"kv-camera","title":"参照動画：台座の上のランニングシューズ","mode":"video_ref","source":"kovapi","official_no":null,"params":{"duration":6,"resolution":"768P","size":"16:9","image_role":"reference"},"cost":"$0.325","video":"https://img.kovapi.com/i/mp-aa7f83de1a85c8445731122b.mp4","poster":"https://img.kovapi.com/i/mp-b19e07fd5ec8d5ede9fa728e.webp","prompt":"The running shoe from image 1 stands on a stone pedestal in the middle of an empty plaza at golden hour. Follow the camera movement and pacing of video 1: a slow arc shot around the subject from left to right, keeping it centered. Do not show the statue from video 1. Sound: soft wind and distant pigeons. No music.","inputs":{"images":["https://img.kovapi.com/i/mp-cc795e889918bc095cfac8c6.jpg"],"video_references":[{"url":"https://img.kovapi.com/i/mp-dd0414d99599d8386d11fbfd.mp4","duration":7}],"audio_reference":[]}},{"id":"kv-dance","title":"参照動画：キツネが同じダンスを踊る","mode":"video_ref","source":"kovapi","official_no":null,"params":{"duration":6,"resolution":"768P","size":"16:9","image_role":"reference"},"cost":"$0.325","video":"https://img.kovapi.com/i/mp-e2308084597964acbd152bce.mp4","poster":"https://img.kovapi.com/i/mp-92c8289f14a4283aaa282069.webp","prompt":"The cartoon red fox in the yellow hoodie from image 1 performs the same dance routine as the dancer in video 1, with the same arm raises, hip sways, spin and ending pose, in a colorful cartoon bedroom. 3D animated style, static full-body shot. Sound: upbeat pop drums and bass, the fox's sneakers tapping on the floor.","inputs":{"images":["https://img.kovapi.com/i/mp-f75baad27af554d861a38176.jpg"],"video_references":[{"url":"https://img.kovapi.com/i/mp-f34bfc40277ff5ab18021caa.mp4","duration":7}],"audio_reference":[]}},{"id":"kv-lite","title":"Lite：ランニングシューズのターンテーブル撮影","mode":"multi_ref","source":"kovapi","official_no":null,"params":{"duration":5,"resolution":"768P","size":"16:9"},"cost":"$0.0625","video":"https://img.kovapi.com/i/mp-5a3d34dd41ce101dcf3825c9.mp4","poster":"https://img.kovapi.com/i/mp-6070620d8ba7464366b13009.webp","prompt":"The running shoe from the reference image rotates slowly on a glossy black turntable while streaks of neon light sweep across it, close studio product shot. Sound: a low electronic hum.","inputs":{"images":["https://img.kovapi.com/i/mp-cc795e889918bc095cfac8c6.jpg"],"video_references":[],"audio_reference":[]}}],"faq":[{"q":"MiniMax H3 とは？","a":"MiniMax が2026年7月に公開した動画モデルで、MiniMax は Hailuo 01、Hailuo 02 に続く第三世代と位置づけています。テキスト・画像・動画・音声をまとめて理解し、どの動画にも音声が付きます。KovAPI では minimax-h3 で、テキストから動画、最初のフレーム、最初と最後のフレーム、参照画像、参照動画に対応します。"},{"q":"どのくらいの長さの動画を作れますか？","a":"4〜15 秒の整数秒で自由に指定でき、duration を省くと 5 秒です。実際の動画は指定より 1 秒未満だけ長くなります（5 秒のジョブで約 5.2 秒）が、課金は指定した秒数で計算します。"},{"q":"解像度はどれを選べばよいですか？実際のサイズは？","a":"試作や大量生成には 480P、精細さと料金のバランスなら 768P、最も精細な映像には 1080P。resolution を省くと 1080P です。16:9 の場合、480P は 864×480、768P は約 1344×768、1080P は約 1920×1080 で、ジョブによって数十ピクセルの差が出ることがあります。"},{"q":"720P を指定できますか？","a":"できます。768P として生成し、768P の料金で課金します。2K や 4K などほかの値は送信時に拒否され、課金されません。"},{"q":"フレーム指定と参照はどう切り替えますか？","a":"image_role を省くと、1 枚なら最初のフレーム、2 枚なら最初と最後のフレームです。image_role: reference を指定すると参照画像になり（最大 9 枚）、写っている人物・商品・場所がフレームとしてではなく画面の中に登場します。参照動画や参照音声には参照モードが必要です。"},{"q":"参照動画で何ができますか？料金は？","a":"動きやカメラワーク、テンポを参照動画に合わせられます。このページのキツネは、参照動画の人と同じ振り付けで踊っています。参照動画の秒数は出力の秒数と合わせて、選んだ解像度の単価で課金します。たとえば 768P で出力 6 秒、参照動画 7 秒なら 13 秒分です。最大 3 本、各 2〜15 秒・合計 15 秒まで。"},{"q":"参照音声は効果がありますか？料金は？","a":"無料で最大 3 本、参照画像か参照動画と一緒に送る必要があります。MiniMax のガイドでは声や音楽の参照として説明されていますが、キャラクターに参照音声の声で新しいセリフを話させたテストでは 2 回とも声ははっきりとは変わらなかったので、声を決める目的では当てにしないでください。"},{"q":"参照素材の形式とサイズの条件は？","a":"画像：JPG / PNG / WEBP（GIF は不可）、1 枚 16MB まで、幅・高さとも 256〜5760 ピクセル、縦横比 0.4〜2.5。標準版の参照モードは最大 9 枚、Lite は最大 5 枚。参照動画（標準版のみ）：MP4 / MOV（映像 H.264 / H.265、音声 AAC / MP3）、最大 3 本、各 2〜15 秒・合計 15 秒まで、1 本 50MB まで。参照音声（標準版のみ）：WAV / MP3、最大 3 本、各 2〜15 秒・合計 15 秒まで、1 本 15MB まで。条件に合わないものは送信時に拒否されます（コーデックが違う場合は生成中に失敗します）。いずれも課金されません。"},{"q":"音声をオフにできますか？","a":"できません。どの動画にも音声トラックが付き、audio: false は拒否されます。音楽が不要なら non_diegetic_music: N/A と書き、無音のファイルが必要ならダウンロード後に音声トラックを削除してください。"},{"q":"セリフは中国語やほかの言語でも書けますか？","a":"書けます。セリフは <d>[Chinese] …</d> の形で書きます。私たちのテストでは中国語のセリフは一字一句そのとおりに出ましたが、画面下部に中国語の字幕が出て、字幕なしを指示しても消えませんでした。MiniMax によると、セリフは中国語・英語・日本語・韓国語・スペイン語・ロシア語など 11 言語で安定しています。プロンプトのほかの部分は、ガイドと同じく英語で書くほうが確実です。"},{"q":"実在の人物の写真を使えますか？","a":"使えます。一般の人の写真 2 枚で、最初のフレームとして 2 回、参照として 2 回試し、4 回とも正常に生成されました。写っている人物の肖像を使う権利があることを確認してください。"},{"q":"生成にどのくらいかかりますか？","a":"2026年11月12日に行った 30 本あまりのテスト生成では、ほとんどが 2〜6 分で完了し、15 分を超えたものもいくつかありました。解像度が高いほど、参照素材が多いほど、また混雑時ほど時間がかかります。非同期ジョブなので、ジョブ ID でポーリングするか、callback_url を指定して通知を待ってください。"},{"q":"生成に失敗したら課金されますか？","a":"失敗した生成は課金されず、そのまま再送信できます。送信時の仮押さえは全額返金され、同じジョブの自動リトライは一度だけ精算されます。"},{"q":"動画はどのくらい保存されますか？","a":"生成した動画とアップロードした素材は 7 日間保存され、その後削除されます。必要なものはダウンロードしておいてください。"},{"q":"H3 と H3 Lite はどちらを選べばよいですか？","a":"MiniMax H3 Lite は同じ H3 を少ない推論ステップで動かすもので、速くて安い反面、画質はやや下がります。480P / 768P のみで、テキストと参照画像だけに対応し、参照音声・参照動画は使えません。Lite でプロンプトや構図を試し、仕上げは H3 の 1080P で生成してください。違いは上の同じプロンプトでの比較で確かめられます。"},{"q":"H3、Wan 3.0、Seedance 2.5 はどう選べばよいですか？","a":"15 秒を超える動画なら Wan 3.0 か Seedance 2.5（最長 30 秒）、最初と最後のフレームや安い 480P の試作なら H3 が向いています。いちばん確実なのは、同じプロンプトをそれぞれで試して比べることです。"},{"q":"このページの作例はどうやって作りましたか？","a":"すべて KovAPI が自社の API で、表示している設定のとおりに生成したものです。各作例には設定と、現在の料金で計算した費用を載せています。プロンプトの多くは MiniMax 公式のガイドから一字一句そのまま引用し、入力画像は KovAPI の画像モデルで作成しました。"}],"notes_for_ai":["モデル ID は minimax-h3。POST /v1/videos/generations で送信すると HTTP 202 とジョブ id が返ります。結果は GET /v1/videos/jobs/ にジョブ ID を付けて取得します。","resolution は 480P / 768P / 1080P のいずれかで既定は 1080P。720P は 768P として扱います。size は 16:9 / 9:16 / 1:1 / 4:3 / 3:4 / 3:2 / 2:3 / 21:9 のいずれか。duration は 4〜15 の整数で既定は 5。","画像は images へ：image_role を省くと 1 枚は最初のフレーム、2 枚は最初と最後のフレーム。image_role: reference なら参照画像を最大 9 枚で、3 枚以上では reference の指定が必須です。","参照動画のフィールドは video_references（または video_reference）：最大 3 本、各 2〜15 秒・合計 15 秒以内、MP4 / MOV、秒単位で課金。参照音声のフィールドは audio_references（または audio_reference）：最大 3 本、WAV / MP3、各 2〜15 秒・合計 15 秒以内、URL のみ、無料で、参照画像か参照動画と一緒のときだけ使えます。どちらも参照モードが必要です。","reference_audios、reference_videos、start_frame、end_frame、および最初のフレームのリクエストに付けた音声・動画は、送信時に HTTP 400 を返し、課金されません。","課金：選んだ解像度の秒単価 ×（出力の秒数 + 参照動画の秒数）。480P $0.015/秒、768P $0.025/秒、1080P $0.036/秒。","動画には常に音声トラックが付き、audio: false は拒否されます。プロンプトは 5,000 文字までで、このページのプロンプトのセクションで示した構成で書きます。実測：参照音声で声ははっきりとは変わりませんでした。中国語のセリフには字幕が焼き込まれます。"],"versus":[{"id":"tiers","title":"ラテアート：H3 の 3 段階と Lite の 2 段階","params":{"duration":5,"size":"16:9"},"prompt":"integrated_multimodal_description: [Shot 1] Live-action, cinematic, a close shot of a barista's hands pouring steamed milk into a cup of espresso on a wooden counter by a sunny window. The milk forms a heart in the crema while steam curls upward, and the camera pushes in with small amplitude at slow speed toward the cup.\n\noverall_soundscape: Milk streams into the cup, a steam wand hisses softly in the background and cafe chatter murmurs.\n\nnon_diegetic_music: N/A","clips":[{"model":"minimax-h3","resolution":"1080P","video":"https://img.kovapi.com/i/mp-30a37c4381ec04a2ba543aab.mp4","cost":"$0.18","verdict":"最も鮮明。ラテの模様、ピッチャーの映り込み、カップの縁までくっきりしています。"},{"model":"minimax-h3","resolution":"768P","video":"https://img.kovapi.com/i/mp-2972abbc7c033fb49b25783d.mp4","cost":"$0.125","verdict":"1080P よりディテールはやや少ないものの、十分きれいです。"},{"model":"minimax-h3","resolution":"480P","video":"https://img.kovapi.com/i/mp-faf663f1a053b4a823c2ea31.mp4","cost":"$0.075","verdict":"構図と動きははっきりわかりますが、拡大すると甘くなります。試作向きです。"},{"model":"minimax-h3-lite","resolution":"768P","video":"https://img.kovapi.com/i/mp-4eda7882119d1b49c37bf0e1.mp4","cost":"$0.0625","verdict":"速くて安い反面、ラテの模様ははっきり弱くなります。"},{"model":"minimax-h3-lite","resolution":"480P","video":"https://img.kovapi.com/i/mp-10b056d268a7c3beaf4f26e0.mp4","cost":"$0.025","verdict":"最も安く、構図と動きの確認にだけ向いています。"}]}]}