Skip to content

Record your screen, ship a demo. Free and open-source, GPU-accelerated, no watermarks, no subscriptions. Windows, macOS, Linux. Actively maintained.

docs(mcp): describe the clip tools, and stop promising to split a clip

EtienneLescot3592c658c2d5
diff --git a/skills/openscreen-demo/SKILL.md b/skills/openscreen-demo/SKILL.md
index 19c3025bd..3918a420b 100644
--- a/skills/openscreen-demo/SKILL.md
+++ b/skills/openscreen-demo/SKILL.md
@@ -82,7 +82,8 @@ Use the document tools, always with the `projectId`. Read the project first with
- **Format first:** `setAspectRatio` for where the video will be shown, `16:9` for X. Do it before placing text.
- **Cut dead time:** the setup at the start, the stop at the end, any wait. Use `addTrims`, or `addSpeed` to fast-forward a wait instead of cutting it.
-- **Zoom on the action:** clicks close in time and on screen share one zoom, and the first 2.5 s stay wide. Check them, then add or move zooms with `addZooms` and `setZoom` where a result deserves its own. Hold a zoom at least 1.5 s.
+- **Zoom on the action:** clicks close in time and on screen share one zoom, and the first 2.5 s stay wide. Check them, then add or move zooms with `addZooms` and `setZoom` where a result deserves its own. Hold a zoom at least 1.5 s. After a cut that removed some, `addAutoZooms` plans them again on the clicks left, clear of the zooms still there.
+- **Frame the app:** when the take shows more than the app, `setClipRange` with a `cropRegion` crops the clip to it.
- **Callouts:** one `addAnnotation` per beat, short, placed clear of the action. Text sits on the output frame and stays put when the picture zooms. Use its look for hierarchy: a large title with `animation: "typewriter"`, step callouts with `animation: "pop"`. An arrow, `type: "figure"`, points at a control the text names. `setAnnotation` moves or restyles one.
- **Hide what is private:** an email address, a token or a name that shows on screen gets `addAnnotation` with `type: "blur"` over the span it is visible. Its x, y, width and height are percent of the recording's picture, not of the frame, so it stays on what it hides when a zoom moves the picture. Check it with `getFrames`.
- **Music or a voiceover:** `importMedia` with the file's absolute path adds it to the project's media, then `addAudio` plays it over a span. `removeMedia` takes back a file the timeline no longer uses.
diff --git a/src/i18n/locales/ar/editor.json b/src/i18n/locales/ar/editor.json
index da053d2d7..157133a4b 100644
--- a/src/i18n/locales/ar/editor.json
+++ b/src/i18n/locales/ar/editor.json
@@ -273,7 +273,7 @@
"subtitle": "تعمل المحادثة على تعديل الفيديو عبر التحدث إلى نموذج لغوي. اختر المزوّد الذي تثق به واربط مفتاح API للبدء.",
"feature1": "اقطع الصمت، اضغط الوقفات، أزل الكلمات الحشوية",
"feature2": "أضف ترجمات، كبّر الكاميرا، أنشئ عنواناً",
- "feature3": "أعد كتابة قسم، أو أعِد صياغته، أو قسّم مقطعاً عند الطلب",
+ "feature3": "أعد كتابة قسم، أو أعِد صياغته، أو أعِد ترتيب المقاطع عند الطلب",
"cta": "إعداد مزوّد",
"disclaimer": "سيُرسَل نصّ فيديوك إلى المزوّد الذي تختاره. لا يُشارَك شيء قبل أن تربط مزوّداً."
},
diff --git a/src/i18n/locales/cs/editor.json b/src/i18n/locales/cs/editor.json
index 086d3f74b..f4720fa9c 100644
--- a/src/i18n/locales/cs/editor.json
+++ b/src/i18n/locales/cs/editor.json
@@ -273,7 +273,7 @@
"subtitle": "Chat upravuje vaše video prostřednictvím komunikace s jazykovým modelem. Vyberte poskytovatele, kterému důvěřujete, a připojte API klíč pro začátek.",
"feature1": "Vystřihnout ticho, zkrátit pauzy, odstranit výplňová slova",
"feature2": "Přidat titulky, přiblížit kameru, generovat název",
- "feature3": "Přepsat sekci, přeformulovat nebo rozdělit klip na žádost",
+ "feature3": "Přepsat sekci, přeformulovat nebo přeskládat klipy na žádost",
"cta": "Nastavit poskytovatele",
"disclaimer": "Přepis vašeho videa bude odeslán vámi zvolenému poskytovateli. Nic není sdíleno, dokud ho nepřipojíte."
},
diff --git a/src/i18n/locales/de/editor.json b/src/i18n/locales/de/editor.json
index eb9a7fdf9..c452cd77e 100644
--- a/src/i18n/locales/de/editor.json
+++ b/src/i18n/locales/de/editor.json
@@ -273,7 +273,7 @@
"subtitle": "Der Chat bearbeitet dein Video, indem er mit einem Sprachmodell spricht. Wähle einen Anbieter, dem du vertraust, und verbinde einen API-Schlüssel, um loszulegen.",
"feature1": "Stille schneiden, Pausen straffen, Füllwörter entfernen",
"feature2": "Untertitel hinzufügen, auf die Kamera zoomen, einen Titel erzeugen",
- "feature3": "Einen Abschnitt umschreiben, umformulieren oder auf Wunsch einen Clip teilen",
+ "feature3": "Einen Abschnitt umschreiben, umformulieren oder auf Wunsch Clips neu anordnen",
"cta": "Anbieter einrichten",
"disclaimer": "Das Transkript deines Videos wird an den Anbieter gesendet, den du wählst. Es wird nichts geteilt, bevor du einen verbindest."
},
diff --git a/src/i18n/locales/en/editor.json b/src/i18n/locales/en/editor.json
index 8e6d253d9..8c0db248e 100644
--- a/src/i18n/locales/en/editor.json
+++ b/src/i18n/locales/en/editor.json
@@ -273,7 +273,7 @@
"subtitle": "The chat edits your video by talking to a language model. Pick a provider you trust and connect an API key to get started.",
"feature1": "Cut silences, tighten pauses, drop filler words",
"feature2": "Add captions, zoom on the camera, generate a title",
- "feature3": "Rewrite a section, rephrase, or split a clip on request",
+ "feature3": "Rewrite a section, rephrase, or rearrange clips on request",
"cta": "Set up a provider",
"disclaimer": "Your video's transcript will be sent to the provider you choose. Nothing is shared until you connect one."
},
diff --git a/src/i18n/locales/es/editor.json b/src/i18n/locales/es/editor.json
index 680632caa..f11ca3013 100644
--- a/src/i18n/locales/es/editor.json
+++ b/src/i18n/locales/es/editor.json
@@ -273,7 +273,7 @@
"subtitle": "El chat edita tu vídeo hablando con un modelo de lenguaje. Elige el proveedor que prefieras y conecta una clave de API para empezar.",
"feature1": "Corta silencios, aprieta pausas, elimina muletillas",
"feature2": "Añade subtítulos, hace zoom a la cámara, genera un título",
- "feature3": "Reescribe una sección, reformula o divide un clip bajo pedido",
+ "feature3": "Reescribe una sección, reformula o reordena los clips bajo pedido",
"cta": "Configurar un proveedor",
"disclaimer": "La transcripción de tu vídeo se enviará al proveedor que elijas. No se comparte nada hasta que conectes uno."
},
diff --git a/src/i18n/locales/fr/editor.json b/src/i18n/locales/fr/editor.json
index 6fd774cd6..b624ccafc 100644
--- a/src/i18n/locales/fr/editor.json
+++ b/src/i18n/locales/fr/editor.json
@@ -273,7 +273,7 @@
"subtitle": "Le chat édite votre vidéo en discutant avec un modèle de langage. Choisissez le fournisseur auquel vous faites confiance et connectez une clé API pour commencer.",
"feature1": "Couper les silences, resserrer les pauses, supprimer les tics de langage",
"feature2": "Ajouter des sous-titres, zoomer sur la caméra, générer un titre",
- "feature3": "Réécrire une section, reformuler ou découper un clip à la demande",
+ "feature3": "Réécrire une section, reformuler ou réorganiser les clips à la demande",
"cta": "Configurer un fournisseur",
"disclaimer": "La transcription de votre vidéo sera envoyée au fournisseur que vous choisissez. Rien n'est partagé tant que vous n'en connectez pas un."
},
diff --git a/src/i18n/locales/it/editor.json b/src/i18n/locales/it/editor.json
index 27fd5cf6c..d51b0c87a 100644
--- a/src/i18n/locales/it/editor.json
+++ b/src/i18n/locales/it/editor.json
@@ -273,7 +273,7 @@
"subtitle": "La chat modifica il tuo video parlando con un modello linguistico. Scegli il fornitore di cui ti fidi e collega una chiave API per iniziare.",
"feature1": "Taglia i silenzi, stringi le pause, elimina le parole superflue",
"feature2": "Aggiungi sottotitoli, ingrandisci la camera, genera un titolo",
- "feature3": "Riscrivi una sezione, riformula o dividi un clip su richiesta",
+ "feature3": "Riscrivi una sezione, riformula o riordina i clip su richiesta",
"cta": "Configura un fornitore",
"disclaimer": "La trascrizione del tuo video verrà inviata al fornitore che scegli. Nulla viene condiviso finché non ne colleghi uno."
},
diff --git a/src/i18n/locales/ja-JP/editor.json b/src/i18n/locales/ja-JP/editor.json
index 3de6f0a77..14fc00c54 100644
--- a/src/i18n/locales/ja-JP/editor.json
+++ b/src/i18n/locales/ja-JP/editor.json
@@ -273,7 +273,7 @@
"subtitle": "チャットは言語モデルと会話しながら動画を編集します。信頼できるプロバイダーを選んで API キーを接続すれば始められます。",
"feature1": "無音部分をカットし、間を詰め、つなぎ言葉を削除",
"feature2": "字幕を追加し、カメラをズームし、タイトルを生成",
- "feature3": "セクションを言い換えたり、書き直したり、クリップを分割",
+ "feature3": "セクションを言い換えたり、書き直したり、クリップを並べ替え",
"cta": "プロバイダーを設定",
"disclaimer": "動画の文字起こしは、選択したプロバイダーに送信されます。接続するまでは何も共有されません。"
},
diff --git a/src/i18n/locales/ko-KR/editor.json b/src/i18n/locales/ko-KR/editor.json
index 77731a1d3..47b8fc67d 100644
--- a/src/i18n/locales/ko-KR/editor.json
+++ b/src/i18n/locales/ko-KR/editor.json
@@ -273,7 +273,7 @@
"subtitle": "채팅은 언어 모델과 대화하며 영상을 편집합니다. 신뢰하는 공급자를 골라 API 키를 연결하면 시작할 수 있습니다.",
"feature1": "무음을 잘라내고, 끊김을 줄이며, 군더더기 말을 지웁니다",
"feature2": "자막을 추가하고, 카메라를 확대하며, 제목을 만듭니다",
- "feature3": "원하는 대로 구간을 다시 쓰고, 표현을 바꾸거나 클립을 나눕니다",
+ "feature3": "원하는 대로 구간을 다시 쓰고, 표현을 바꾸거나 클립 순서를 바꿉니다",
"cta": "공급자 설정",
"disclaimer": "영상 전사본은 선택한 공급자에게 전송됩니다. 공급자를 연결하기 전까지는 아무것도 공유되지 않습니다."
},
diff --git a/src/i18n/locales/pt-BR/editor.json b/src/i18n/locales/pt-BR/editor.json
index 55e1fa5bf..8dbac331a 100644
--- a/src/i18n/locales/pt-BR/editor.json
+++ b/src/i18n/locales/pt-BR/editor.json
@@ -273,7 +273,7 @@
"subtitle": "O chat edita o seu vídeo conversando com um modelo de linguagem. Escolha o fornecedor em que confia e conecte uma chave de API para começar.",
"feature1": "Corta silêncios, aperta pausas, remove vícios de linguagem",
"feature2": "Adiciona legendas, aplica zoom na câmera, gera um título",
- "feature3": "Reescreve uma seção, reformula ou divide um clipe sob pedido",
+ "feature3": "Reescreve uma seção, reformula ou reorganiza os clipes sob pedido",
"cta": "Configurar um fornecedor",
"disclaimer": "A transcrição do seu vídeo será enviada ao fornecedor que escolher. Nada é compartilhado até você conectar um."
},
diff --git a/src/i18n/locales/ru/editor.json b/src/i18n/locales/ru/editor.json
index c89607df1..05b049cba 100644
--- a/src/i18n/locales/ru/editor.json
+++ b/src/i18n/locales/ru/editor.json
@@ -273,7 +273,7 @@
"subtitle": "Чат редактирует видео через языковую модель. Выберите провайдера, которому доверяете, и подключите API-ключ, чтобы начать.",
"feature1": "Вырезает тишину, сокращает паузы, убирает слова-паразиты",
"feature2": "Добавляет субтитры, зум на камеру, генерирует заголовок",
- "feature3": "Переписывает раздел, перефразирует или разрезает клип по запросу",
+ "feature3": "Переписывает раздел, перефразирует или переставляет клипы по запросу",
"cta": "Настроить провайдера",
"disclaimer": "Транскрипция вашего видео будет отправлена выбранному провайдеру. Пока вы не подключите провайдера, ничего не отправляется."
},
diff --git a/src/i18n/locales/tr/editor.json b/src/i18n/locales/tr/editor.json
index f052f504e..8f6fe686a 100644
--- a/src/i18n/locales/tr/editor.json
+++ b/src/i18n/locales/tr/editor.json
@@ -273,7 +273,7 @@
"subtitle": "Sohbet, videonuzu bir dil modeliyle konuşarak düzenler. Güvendiğiniz sağlayıcıyı seçin ve başlamak için bir API anahtarı bağlayın.",
"feature1": "Sessizlikleri keser, duraklamaları sıkılaştırır, dolgu kelimeleri kaldırır",
"feature2": "Altyazı ekler, kameraya yakınlaştırır, başlık üretir",
- "feature3": "Bir bölümü yeniden yazar, ifadeyi değiştirir veya klibi isteğe göre böler",
+ "feature3": "Bir bölümü yeniden yazar, ifadeyi değiştirir veya klipleri isteğe göre yeniden sıralar",
"cta": "Sağlayıcı kur",
"disclaimer": "Videonuzun transkripsiyonu seçtiğiniz sağlayıcıya gönderilecek. Bir sağlayıcı bağlamadan hiçbir şey paylaşılmaz."
},
diff --git a/src/i18n/locales/vi/editor.json b/src/i18n/locales/vi/editor.json
index f85a6e755..d484dc4bd 100644
--- a/src/i18n/locales/vi/editor.json
+++ b/src/i18n/locales/vi/editor.json
@@ -273,7 +273,7 @@
"subtitle": "Chat chỉnh sửa video của bạn bằng cách trò chuyện với một mô hình ngôn ngữ. Hãy chọn nhà cung cấp bạn tin tưởng và kết nối khóa API để bắt đầu.",
"feature1": "Cắt khoảng lặng, rút ngắn nhịp nghỉ, loại bỏ từ đệm",
"feature2": "Thêm phụ đề, zoom vào camera, tạo tiêu đề",
- "feature3": "Viết lại một đoạn, diễn đạt khác hoặc tách clip theo yêu cầu",
+ "feature3": "Viết lại một đoạn, diễn đạt khác hoặc sắp xếp lại clip theo yêu cầu",
"cta": "Thiết lập nhà cung cấp",
"disclaimer": "Bản chép lời video sẽ được gửi đến nhà cung cấp bạn chọn. Không có gì được chia sẻ cho đến khi bạn kết nối một nhà cung cấp."
},
diff --git a/src/i18n/locales/zh-CN/editor.json b/src/i18n/locales/zh-CN/editor.json
index 940a28963..5a7413051 100644
--- a/src/i18n/locales/zh-CN/editor.json
+++ b/src/i18n/locales/zh-CN/editor.json
@@ -273,7 +273,7 @@
"subtitle": "聊天通过与语言模型对话来编辑你的视频。选择你信任的提供方并连接一个 API 密钥即可开始。",
"feature1": "剪掉静音、收紧停顿、去除口头禅",
"feature2": "添加字幕、为镜头变焦、生成标题",
- "feature3": "按需重写章节、换种说法或拆分片段",
+ "feature3": "按需重写章节、换种说法或重新排列片段",
"cta": "设置提供方",
"disclaimer": "你视频的转录文本将发送到你选择的提供方。在你连接之前不会共享任何内容。"
},
diff --git a/src/i18n/locales/zh-TW/editor.json b/src/i18n/locales/zh-TW/editor.json
index 54fe4028e..5019e3f07 100644
--- a/src/i18n/locales/zh-TW/editor.json
+++ b/src/i18n/locales/zh-TW/editor.json
@@ -273,7 +273,7 @@
"subtitle": "聊天透過與語言模型對話來編輯你的影片。選擇你信任的提供者並連接一個 API 金鑰即可開始。",
"feature1": "剪輯靜音、收緊停頓、去除口頭禪",
"feature2": "新增字幕、為鏡頭變焦、產生標題",
- "feature3": "依需求重寫段落、換種說法或分割片段",
+ "feature3": "依需求重寫段落、換種說法或重新排列片段",
"cta": "設定提供者",
"disclaimer": "你影片的轉錄文字會送到你選擇的提供者。在你連接之前不會分享任何內容。"
},
diff --git a/technical-documentation/architecture/mcp-server.md b/technical-documentation/architecture/mcp-server.md
index 555ebfd7d..e8ebb85f1 100644
--- a/technical-documentation/architecture/mcp-server.md
+++ b/technical-documentation/architecture/mcp-server.md
@@ -34,7 +34,7 @@ The same tools are served over two transports, by two different processes:
## One tool surface, two agents
-Nothing about the tools is reimplemented. The server registers `TOOL_ARG_SCHEMAS` (names and zod schemas) and `TOOL_DESCRIPTIONS`, and builds its `instructions` around `buildSystemPrompt`, all exported from [`deep-agent/service.ts`](../../electron/ai-edition/deep-agent/service.ts), where `buildTools` builds the in-app agent from the same table. Every call goes through `runDocumentTool`, the function the in-app agent's `documentTool` also calls: the cursor-telemetry read the zoom tools need, then `executeAgentTool`.
+Nothing about the tools is reimplemented. The server registers `TOOL_ARG_SCHEMAS` (names and zod schemas) and `TOOL_DESCRIPTIONS`, and builds its `instructions` around `buildSystemPrompt`, all exported from [`deep-agent/service.ts`](../../electron/ai-edition/deep-agent/service.ts), where `buildTools` builds the in-app agent from the same table. Every call goes through `runDocumentTool`, the function the in-app agent's `documentTool` also calls: the cursor-telemetry read the zoom tools need (for `addAutoZooms`, the timeline wand's plan, `collectAutoZoomSuggestionsForDocument`, over every take on the timeline), then `executeAgentTool`.
So a tool added to the agent appears over MCP with no further work, and the MCP test asserts the listed tools equal `listProjects`, then `OPENSCREEN_TOOL_NAMES`, then the three project tools, then the two checkpoint tools, then the [media tools](#the-media-tools). What the server adds:
diff --git a/website/docs/ai-editing.md b/website/docs/ai-editing.md
index 2a6d13204..7e76f2ca9 100644
--- a/website/docs/ai-editing.md
+++ b/website/docs/ai-editing.md
@@ -41,7 +41,7 @@ The ChatGPT and GitHub Copilot sign-in options were **removed in 1.8.0**. They w
## Using the agent
-Describe the edit in plain language — "cut the dead air in the intro", "zoom in when I open the terminal". The agent works through real, undoable timeline operations, not a re-render: it can add and adjust trims, zooms, speed regions, annotations (text, arrows, and blurs that hide private details on screen), imported audio tracks with their fades, and Full Camera segments, edit clip in/out points, reorder or remove clips, and read the transcript to find what you're referring to. It also sets the look of the video: background, padding, rounded corners, shadow, device frame, format, the camera layout, the cursor and the master volume.
+Describe the edit in plain language — "cut the dead air in the intro", "zoom in when I open the terminal". The agent works through real, undoable timeline operations, not a re-render: it can add and adjust trims, zooms, speed regions, annotations (text, arrows, and blurs that hide private details on screen), imported audio tracks with their fades, and Full Camera segments, add automatic zooms on your clicks, edit a clip's in/out points and crop, place another source's footage, duplicate, reorder or remove clips, and read the transcript to find what you're referring to. It also sets the look of the video: background, padding, rounded corners, shadow, device frame, format, the camera layout, the cursor and the master volume.
The panel around it:
diff --git a/website/i18n/de/docusaurus-plugin-content-docs/current/ai-editing.md b/website/i18n/de/docusaurus-plugin-content-docs/current/ai-editing.md
index ca10e9f4d..0e5bed04e 100644
--- a/website/i18n/de/docusaurus-plugin-content-docs/current/ai-editing.md
+++ b/website/i18n/de/docusaurus-plugin-content-docs/current/ai-editing.md
@@ -41,7 +41,7 @@ Die Anmeldeoptionen für ChatGPT und GitHub Copilot wurden **in 1.8.0 entfernt**
## Den Agenten nutzen {#using-the-agent}
-Beschreibe die Änderung in Alltagssprache, etwa „schneide die Stille im Intro heraus“ oder „zoome hinein, wenn ich das Terminal öffne“. Der Agent arbeitet mit echten, rückgängig machbaren Operationen auf der Zeitleiste, nicht mit einem neuen Rendering: Er kann Schnitte, Zooms, Geschwindigkeitsbereiche, Annotationen (Text, Pfeile und Unschärfen, die private Details auf dem Bildschirm verbergen), importierte Audiospuren samt Ein- und Ausblendung und Full-Camera-Segmente hinzufügen und anpassen, Start- und Endpunkte von Clips ändern, Clips umsortieren oder entfernen und das Transkript lesen, um herauszufinden, was du meinst. Außerdem stellt er das Aussehen des Videos ein: Hintergrund, Innenabstand, abgerundete Ecken, Schatten, Geräterahmen, Format, das Kamera-Layout, den Cursor und die Gesamtlautstärke.
+Beschreibe die Änderung in Alltagssprache, etwa „schneide die Stille im Intro heraus“ oder „zoome hinein, wenn ich das Terminal öffne“. Der Agent arbeitet mit echten, rückgängig machbaren Operationen auf der Zeitleiste, nicht mit einem neuen Rendering: Er kann Schnitte, Zooms, Geschwindigkeitsbereiche, Annotationen (Text, Pfeile und Unschärfen, die private Details auf dem Bildschirm verbergen), importierte Audiospuren samt Ein- und Ausblendung und Full-Camera-Segmente hinzufügen und anpassen, automatische Zooms auf deine Klicks setzen, Start- und Endpunkte und den Zuschnitt eines Clips ändern, Material einer anderen Quelle platzieren, Clips duplizieren, umsortieren oder entfernen und das Transkript lesen, um herauszufinden, was du meinst. Außerdem stellt er das Aussehen des Videos ein: Hintergrund, Innenabstand, abgerundete Ecken, Schatten, Geräterahmen, Format, das Kamera-Layout, den Cursor und die Gesamtlautstärke.
Der Bereich drumherum:
diff --git a/website/i18n/es/docusaurus-plugin-content-docs/current/ai-editing.md b/website/i18n/es/docusaurus-plugin-content-docs/current/ai-editing.md
index 02162af31..a31d46c26 100644
--- a/website/i18n/es/docusaurus-plugin-content-docs/current/ai-editing.md
+++ b/website/i18n/es/docusaurus-plugin-content-docs/current/ai-editing.md
@@ -41,7 +41,7 @@ Las opciones de inicio de sesión con ChatGPT y GitHub Copilot se **eliminaron e
## Usar el agente {#using-the-agent}
-Describe la edición con tus propias palabras: "corta el tiempo muerto de la introducción", "haz zoom cuando abro la terminal". El agente trabaja con operaciones reales de la línea de tiempo, que se pueden deshacer, y no con un nuevo renderizado: puede agregar y ajustar recortes, zooms, regiones de velocidad, anotaciones (texto, flechas y desenfoques que ocultan datos privados en pantalla), pistas de audio importadas con sus fundidos y segmentos de cámara a pantalla completa, editar los puntos de entrada y salida de los clips, reordenar o quitar clips, y leer la transcripción para encontrar aquello a lo que te refieres. También ajusta el aspecto del vídeo: fondo, margen, esquinas redondeadas, sombra, marco de dispositivo, formato, la disposición de la cámara, el cursor y el volumen general.
+Describe la edición con tus propias palabras: "corta el tiempo muerto de la introducción", "haz zoom cuando abro la terminal". El agente trabaja con operaciones reales de la línea de tiempo, que se pueden deshacer, y no con un nuevo renderizado: puede agregar y ajustar recortes, zooms, regiones de velocidad, anotaciones (texto, flechas y desenfoques que ocultan datos privados en pantalla), pistas de audio importadas con sus fundidos y segmentos de cámara a pantalla completa, agregar zooms automáticos en tus clics, editar los puntos de entrada y salida y el recorte de un clip, colocar el material de otra fuente, duplicar, reordenar o quitar clips, y leer la transcripción para encontrar aquello a lo que te refieres. También ajusta el aspecto del vídeo: fondo, margen, esquinas redondeadas, sombra, marco de dispositivo, formato, la disposición de la cámara, el cursor y el volumen general.
El panel que lo rodea:
diff --git a/website/i18n/fr/docusaurus-plugin-content-docs/current/ai-editing.md b/website/i18n/fr/docusaurus-plugin-content-docs/current/ai-editing.md
index 4c7bacfd7..e7f7e5066 100644
--- a/website/i18n/fr/docusaurus-plugin-content-docs/current/ai-editing.md
+++ b/website/i18n/fr/docusaurus-plugin-content-docs/current/ai-editing.md
@@ -41,7 +41,7 @@ Les options de connexion ChatGPT et GitHub Copilot ont été **supprimées dans
## Utiliser l'agent {#using-the-agent}
-Décrivez la modification en langage courant : « coupe les temps morts de l'intro », « zoome quand j'ouvre le terminal ». L'agent travaille avec de vraies opérations de timeline annulables, pas avec un nouveau rendu : il peut ajouter et ajuster des coupes, des zooms, des régions de vitesse, des annotations (texte, flèches et flous qui masquent une information privée à l'écran), des pistes audio importées avec leurs fondus, et des segments Caméra plein écran, modifier les points d'entrée et de sortie des clips, réordonner ou retirer des clips, et lire la transcription pour trouver ce dont vous parlez. Il règle aussi l'apparence de la vidéo : fond, marge, coins arrondis, ombre, cadre d'appareil, format, disposition de la caméra, curseur et volume général.
+Décrivez la modification en langage courant : « coupe les temps morts de l'intro », « zoome quand j'ouvre le terminal ». L'agent travaille avec de vraies opérations de timeline annulables, pas avec un nouveau rendu : il peut ajouter et ajuster des coupes, des zooms, des régions de vitesse, des annotations (texte, flèches et flous qui masquent une information privée à l'écran), des pistes audio importées avec leurs fondus, et des segments Caméra plein écran, ajouter des zooms automatiques sur vos clics, modifier les points d'entrée et de sortie et le recadrage d'un clip, placer les images d'une autre source, dupliquer, réordonner ou retirer des clips, et lire la transcription pour trouver ce dont vous parlez. Il règle aussi l'apparence de la vidéo : fond, marge, coins arrondis, ombre, cadre d'appareil, format, disposition de la caméra, curseur et volume général.
Le panneau qui l'entoure :
diff --git a/website/i18n/ja/docusaurus-plugin-content-docs/current/ai-editing.md b/website/i18n/ja/docusaurus-plugin-content-docs/current/ai-editing.md
index bbc2f3ceb..ba14ba492 100644
--- a/website/i18n/ja/docusaurus-plugin-content-docs/current/ai-editing.md
+++ b/website/i18n/ja/docusaurus-plugin-content-docs/current/ai-editing.md
@@ -41,7 +41,7 @@ ChatGPT と GitHub Copilot のサインインは、**1.8.0 で削除されまし
## エージェントを使う {#using-the-agent}
-行いたい編集を、普段の言葉で伝えます(「イントロの無音部分をカットして」「ターミナルを開いたところでズームして」など)。エージェントは再レンダリングではなく、元に戻せる実際のタイムライン操作で作業します。トリム、ズーム、再生速度の範囲、注釈(テキスト、矢印、画面上の個人情報を隠すぼかし)、取り込んだオーディオトラックとそのフェード、フルスクリーンカメラのセグメントの追加と調整、クリップのイン点とアウト点の編集、クリップの並べ替えと削除ができ、文字起こしを読んで、あなたが指している箇所を見つけます。背景、余白、角の丸み、影、デバイスフレーム、フォーマット、カメラのレイアウト、カーソル、全体の音量といった動画の見た目も設定できます。
+行いたい編集を、普段の言葉で伝えます(「イントロの無音部分をカットして」「ターミナルを開いたところでズームして」など)。エージェントは再レンダリングではなく、元に戻せる実際のタイムライン操作で作業します。トリム、ズーム、再生速度の範囲、注釈(テキスト、矢印、画面上の個人情報を隠すぼかし)、取り込んだオーディオトラックとそのフェード、フルスクリーンカメラのセグメントの追加と調整、クリック位置への自動ズームの追加、クリップのイン点とアウト点やクロップの編集、別のソースの映像の配置、クリップの複製・並べ替え・削除ができ、文字起こしを読んで、あなたが指している箇所を見つけます。背景、余白、角の丸み、影、デバイスフレーム、フォーマット、カメラのレイアウト、カーソル、全体の音量といった動画の見た目も設定できます。
エージェントを囲むパネル:
diff --git a/website/i18n/pt-BR/docusaurus-plugin-content-docs/current/ai-editing.md b/website/i18n/pt-BR/docusaurus-plugin-content-docs/current/ai-editing.md
index 41591063a..fe091b6c8 100644
--- a/website/i18n/pt-BR/docusaurus-plugin-content-docs/current/ai-editing.md
+++ b/website/i18n/pt-BR/docusaurus-plugin-content-docs/current/ai-editing.md
@@ -41,7 +41,7 @@ As opções de login do ChatGPT e do GitHub Copilot foram **removidas na 1.8.0**
## Como usar o agente {#using-the-agent}
-Descreva a edição em linguagem natural — "corte o tempo morto da introdução", "dê zoom quando eu abrir o terminal". O agente trabalha com operações reais da linha do tempo, que podem ser desfeitas, e não com uma nova renderização: ele pode adicionar e ajustar recortes, zooms, regiões de velocidade, anotações (texto, setas e desfoques que escondem dados privados na tela), faixas de áudio importadas com seus fades e segmentos de Câmera em Tela Cheia, editar os pontos de entrada/saída dos clipes, reordenar ou remover clipes e ler a transcrição para encontrar o trecho a que você se refere. Ele também ajusta a aparência do vídeo: fundo, margem, cantos arredondados, sombra, moldura de dispositivo, formato, o layout da câmera, o cursor e o volume geral.
+Descreva a edição em linguagem natural — "corte o tempo morto da introdução", "dê zoom quando eu abrir o terminal". O agente trabalha com operações reais da linha do tempo, que podem ser desfeitas, e não com uma nova renderização: ele pode adicionar e ajustar recortes, zooms, regiões de velocidade, anotações (texto, setas e desfoques que escondem dados privados na tela), faixas de áudio importadas com seus fades e segmentos de Câmera em Tela Cheia, adicionar zooms automáticos nos seus cliques, editar os pontos de entrada/saída e o corte de um clipe, posicionar as imagens de outra fonte, duplicar, reordenar ou remover clipes e ler a transcrição para encontrar o trecho a que você se refere. Ele também ajusta a aparência do vídeo: fundo, margem, cantos arredondados, sombra, moldura de dispositivo, formato, o layout da câmera, o cursor e o volume geral.
O painel em volta dele:
diff --git a/website/i18n/zh-CN/docusaurus-plugin-content-docs/current/ai-editing.md b/website/i18n/zh-CN/docusaurus-plugin-content-docs/current/ai-editing.md
index 785c6d617..f34020ff1 100644
--- a/website/i18n/zh-CN/docusaurus-plugin-content-docs/current/ai-editing.md
+++ b/website/i18n/zh-CN/docusaurus-plugin-content-docs/current/ai-editing.md
@@ -41,7 +41,7 @@ ChatGPT 和 GitHub Copilot 登录选项已**在 1.8.0 中移除**。它们的工
## 使用 AI 代理 {#using-the-agent}
-用日常语言描述你想要的编辑,例如“剪掉开头的空白”“我打开终端时放大画面”。AI 代理通过真实、可撤销的时间轴操作来完成编辑,而不是重新渲染:它可以添加和调整删减区间、缩放、速度区间、标注(文字、箭头,以及遮住屏幕上隐私信息的模糊)、导入的音轨及其淡入淡出和全屏摄像头区间,编辑片段的入点/出点,重新排序或移除片段,还会读取转录文本,找到你所指的内容。它还能设置视频的外观:背景、边距、圆角、阴影、设备边框、画面比例、摄像头布局、光标和总音量。
+用日常语言描述你想要的编辑,例如“剪掉开头的空白”“我打开终端时放大画面”。AI 代理通过真实、可撤销的时间轴操作来完成编辑,而不是重新渲染:它可以添加和调整删减区间、缩放、速度区间、标注(文字、箭头,以及遮住屏幕上隐私信息的模糊)、导入的音轨及其淡入淡出和全屏摄像头区间,在你的点击处添加自动缩放,编辑片段的入点/出点和裁剪,放入另一个素材的画面,复制、重新排序或移除片段,还会读取转录文本,找到你所指的内容。它还能设置视频的外观:背景、边距、圆角、阴影、设备边框、画面比例、摄像头布局、光标和总音量。
它周围的面板包括:
diff --git a/website/i18n/zh-TW/docusaurus-plugin-content-docs/current/ai-editing.md b/website/i18n/zh-TW/docusaurus-plugin-content-docs/current/ai-editing.md
index b6518c020..8d4e69f9f 100644
--- a/website/i18n/zh-TW/docusaurus-plugin-content-docs/current/ai-editing.md
+++ b/website/i18n/zh-TW/docusaurus-plugin-content-docs/current/ai-editing.md
@@ -41,7 +41,7 @@ ChatGPT 與 GitHub Copilot 的登入選項已**在 1.8.0 中移除**。它們的
## 使用代理 {#using-the-agent}
-用一般的語言描述你要的剪輯,例如「剪掉開頭的空檔」、「我打開終端機時放大畫面」。代理會透過真實、可復原的時間軸操作來完成工作,而不是重新算繪:它可以新增與調整剪輯、縮放、速度區域、標註(文字、箭頭,以及遮住畫面上隱私資訊的模糊)、匯入的音軌及其淡入淡出與全螢幕攝影機片段,編輯片段的入點與出點,重新排序或移除片段,也會讀取逐字稿來找出你指的是哪一段。它也能設定影片的外觀:背景、邊距、圓角、陰影、裝置外框、畫面比例、攝影機版面、游標與整體音量。
+用一般的語言描述你要的剪輯,例如「剪掉開頭的空檔」、「我打開終端機時放大畫面」。代理會透過真實、可復原的時間軸操作來完成工作,而不是重新算繪:它可以新增與調整剪輯、縮放、速度區域、標註(文字、箭頭,以及遮住畫面上隱私資訊的模糊)、匯入的音軌及其淡入淡出與全螢幕攝影機片段,在你的點擊處加入自動縮放,編輯片段的入點與出點和裁切,放入另一個來源的畫面,複製、重新排序或移除片段,也會讀取逐字稿來找出你指的是哪一段。它也能設定影片的外觀:背景、邊距、圓角、陰影、裝置外框、畫面比例、攝影機版面、游標與整體音量。
它周圍的面板包括: