Record screen
record_screenRecords the product on a mock (Code record) as a screen-recording clip in a project. Creates blank placeholder clips, registers job entities, and sends the job to AVS.
The blank clips this tool creates are placeholders; they become video clips when processing completes, so removing one loses that scene. Article placeholders are also inserted automatically into plainDoc.
Check how the recording is going with get_recording_activity(project_id). A recording can take hours, so check once rather than polling in a loop.
Requires the Auto-Recording add-on and per-workspace sign-in credentials for the product being recorded. Workspaces without it get back the manual path instead (upload_file, then add_clips(kind='video')) rather than a failure.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"guide_id": "<guide_id>",
"chat_id": "<chat_id>",
"preceding_clip_id": "<preceding_clip_id>",
"scenes": "<scenes>"
},
"name": "record_screen"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| scenes | Yes | REQUIRED — the recording to make, as a list of scenes. This is the ONLY way to specify what to record. A normal single recording is exactly ONE scene; a code-wizard multi-scene / marketing video is N scenes (one clip per scene, and ALL cuts of one video go in a SINGLE record_screen call). A narrated scene REQUIRES a non-empty narration_script; a b-roll scene is silent (no narration, no article). A cut that starts somewhere disconnected is just a scene with entry.mode "fresh". Cleopatra orgs accept exactly ONE narrated scene. Do not set scene_id — it is assigned server-side. | |
| target | No | Which recorder to use when the workspace has both Code record and Browser record: 'code' for a mock of the product, 'browser' for the real product — from the user's request, or their answer when it didn't say. Omit otherwise. | |
| chat_id | Yes | Conversation context ID | |
| guide_id | Yes | Target guide ID | |
| language | No | Language code for the recording (default: en) | en |
| clueprint_id | No | The clueprint this video is built from, if any (the id you passed to get_clueprint). Effects placed automatically on the recording follow that clueprint's effect rules; omit it and they follow the default rules. | |
| voice_version | No | ElevenLabs voice generation for every scene's voice. Leave unset: a named voice uses latest, while a voice the workspace saved and the workspace default keep their own saved version. Use 'legacy' ONLY when the user explicitly asks for the legacy/older voice generation; never choose it yourself. | |
| edit_scene_ids | No | The clip id(s) this edit replaces. Only used when recording_session_id is set; scenes you do not name are not re-filmed. Set preceding_clip_id to the clip you are replacing — an edit naming a clip that is not in the guide is refused rather than appended to the end. | |
| video_intention | No | One-line intent shared across all scenes of a multi-scene recording (e.g. "punchy 30s launch teaser for feature X"). Ignored for single-scene recordings. | |
| preceding_clip_id | Yes | Clip ID after which to insert the new clip | |
| video_script_mode | No | How the narration is treated. 'exact': the user's narration is final and is read word for word; steps the script does not mention play silently. 'near_exact': keep the user's narration word for word, but briefly narrate steps the recording must take that the script does not mention (for example opening a settings dialog to reach something) — use this when the user gives a finished script and did not ask for strictly exact wording. 'rewrite': the narration is a draft and may be reworded to match what was recorded — use this when there is no user script or it is rough. Overrides exact_video_script when both are set. | |
| exact_video_script | No | Legacy flag — prefer video_script_mode instead. Set to true when the video narration must be used exactly as written — the agent that does the recording will not reword, rephrase, or rewrite video_script at all. Default false. | |
| article_script_mode | No | 'exact': the article is used word for word. 'rewrite': the article may be reworded to match the recording. Overrides exact_article_script when both are set. | |
| custom_instructions | No | Optional per-recording instructions (e.g. "select project X", "add rectangle 200x100"). Not related to mocking. | |
| exact_article_script | No | Legacy flag — prefer article_script_mode instead. Set to true when the article must be used exactly as written — the agent that does the recording will not reword, rephrase, or rewrite article_script at all. Default false. | |
| recording_session_id | No | EDIT an existing recording instead of shooting a new one. Pass the recording_session_id from the record_screen that made it, or read it off get_clip. The recorder restores that take's code, notes and click script and changes only what you ask for, which is far faster and cheaper than re-recording. Omit for a fresh recording. Only code-wizard recordings are editable; get_clip omits the field for any clip that is not. |