Panda Video

Confirm that a file was successfully uploaded to a Tutor AI assistant (call after uploading to the presigned URL)

Purchase credits and create a new AI assistant for a video. Returns the created {id, name, status, video_id}.

Create an AI dubbing of a video into one target language. The path follows the video's subtitles, like the dashboard: target already subtitled → audio only (DUBBING, reuses that subtitle); source subtitled → TRANSLATION + dubbing; otherwise TRANSCRIPTION + dubbing (also creates the source subtitle). Costs 5 credits/min (standard AI dubbing, HeyGen audio only) or 14 credits/min (lipsync) per language; minimum 1 min, a partial minute counts only past 1 s. Refuses lipsync on a video that already has standard dubbing (and the inverse), lipsync over 60 min, and a balance below the cost. Returns {video_id, path, from_lang, to_lang, cost_credits, response} — response is the queued work (for TRANSCRIPTION, the transcription work; the dubbing work is created when it finishes).

Create a quiz or mind map WITH CONTENT YOU PROVIDE (no AI, free) in a language that doesn't have one yet — the dashboard's "Add → Create New". Quiz: `questions` (1 to 10, 2 to 5 options each, correct ones marked) and optional `quiz_settings`. Mind map: `topics` (with optional subtopics), `mindmap_theme` (center; default the video title) and optional `mindmap_settings`. The eBook has no manual creation: generate it or upload a PDF (panda_get_ai_ebook_upload_url).

Create a new A/B test. Needs at least 2 videos to start. Returns the created {id, name, status, video_ids}.

Create a custom metadata key-value field for a video (for tagging/categorization). Do NOT use this for chapters, subtitles, CTAs, or player settings — use the specific tools for those. Max 50 fields per video.

Create a new folder. Returns the created {id, name, parent_folder_id}.

Add a domain referrer scoped to a single folder. type is ALLOW|BLOCK. The new row starts in 'pending'. A folder cannot have the same hostname twice. library_id is resolved automatically when omitted. On error the API returns { errCode, errMsg }.

Create a new video funnel

Create a new live stream event. Trial accounts cannot create lives. A quality_package above the plan's maximum is silently lowered to the plan's maximum. Without stream_key_id the account's default stream key is used; a key held by another live (online, provisioning, expired, waiting to start or scheduled within 24h) returns 400. Omitted fields use the API defaults (region us, save_vod true).

Create a new playlist. Videos are REFERENCES — removing from playlist does NOT delete the video. Returns the created {id, name, description, access_type}.

Create a player profile (POST /profile) already configured — colors, controls, caption appearance (colors.captionsColor / captionsBackgroundColor + captionsSize), VSL, save progress, general (speed, theme, gear menu, offline) and availableQualities, all in one call. Send only what you want to set; the rest uses the player defaults. `name` is any label (3–100 chars). The new profile has no videos: link them with panda_apply_profile_to_videos. To make it the account default use panda_set_default_profile. Returns {id, name, isDefault}.

Add one or more library-level domain referrers. Each entry has a hostname and a type (ALLOW|BLOCK, default ALLOW). The same hostname cannot coexist as both ALLOW and BLOCK at the library scope (duplicate check is type-agnostic). New rows start in 'pending' (when domain protection is active) or 'inactive'. library_id is resolved automatically when omitted. On error the API returns { errCode, errMsg }.

Create a new stream key for OBS or other streaming software. The account's first key becomes the default.

Create a new user in the organization. Returns the created {id, name, email, role_id}.

Create a new watermark group

Delete an AI assistant

Delete ONE AI package resource of a video in one language (eBook, mind map or quiz) — cannot be undone: its content, PDF, images and the published file are removed, also for legacy resources. Same as the dashboard's Remove. Refused while it is still generating (checked before deleting; if that check fails nothing is deleted). Other languages and resources stay. To remove a failed generation card use panda_delete_ai_workflow.

Delete an AI work record (e.g. a failed or queued transcription/dubbing card; a queued one is refunded). It doesn't remove what a finished work produced: to remove an eBook, mind map or quiz use panda_delete_ai_resource.

Delete one or more A/B tests

Delete a CTA from a video

Delete a dubbed audio track from a video

Delete a folder by ID. WARNING: All videos and subfolders inside are also deleted (cascade). Goes to trash for 30 days.

Delete one or more folder-level referrers by id (batch). Duplicate ids are de-duplicated; if any id is missing the API returns 404, and if any referrer is library-level it returns 400 ({ errCode, errMsg }). Rows transition to 'deleting' and are removed asynchronously.

Delete a funnel by ID. WARNING: this is destructive. The funnel is removed and the videos inside it go to the trash for 30 days (restoring the funnel's folder brings them back; the funnel does not come back).

Delete one or more live streams

Delete a playlist. Videos are NOT deleted — only the collection is removed.

Delete a player profile. The default profile ('Padrão') cannot be deleted. A profile with no videos is deleted directly. A profile WITH videos needs `strategy` — ask the user which one: 'keep' = each video keeps its current look (gets its own copy of the profile's settings); 'migrate' = the videos move to `target_profile_id`. Up to 5 videos are processed immediately; more are queued (status 'pending') and the profile disappears once all videos are moved. If any video fails, the profile is NOT deleted.

Delete one or more library-level referrers by id (batch). Each referrer must be library-level (folder_id=null) and belong to the library; otherwise the API returns 400 ({ errCode, errMsg }). Rows transition to 'deleting' and are removed asynchronously.

Delete a Shorts job/project

Delete a subaccount

Remove a subtitle from a video by language

Delete a thumbnail from a video (image and its player CTA). Type: 'start' (default, the cover), 'pause', 'end'. For 'pause', thumb_name is required and must be the exact file name — returned by panda_add_pause_thumbnail, or metadata.thumbId of the 'pause' CTA in panda_get_video_player_config. The tool checks the name against the video's pause thumbnails first and refuses (listing the existing names) when it does not match exactly.

Delete a file from a Tutor AI assistant

Remove a user from the organization

Delete one or more videos by ID. Sends to trash for 30 days.

Delete a watermark group

Disable auto-recharge for credits

Disable watermark protection for the account

Download a subtitle file for a specific language

Copy a player profile's settings into a new profile named '<name> (2)', '(3)'… The copy has no videos and is never the default. Exclusive profiles (a single video's own player) cannot be duplicated. Returns {id, name}.

Create a copy of a video. Only works for CONVERTED, non-external, non-funnel videos.

Enable auto-recharge for credits. When balance drops below trigger, recharges action_value.

Enable watermark protection for the account

Turn on Encrypted Anti-Download (HLS encryption) on existing videos, 1–100 per call (one video works too). PAID in credits, per video: ceil(duration in hours × number of current qualities), e.g. a 10-minute video in 3 qualities = 1 credit; charged when the video is queued. Cannot be undone: there is no way to decrypt a video. Only for Gold/Enterprise plans or accounts with the 'Anti-Download Criptografado' add-on (checked before sending; otherwise refused). Videos already encrypted are left out (checked before sending) and listed in skipped as already_encrypted. Videos are also skipped without charge when still processing, with a pending partial deletion, without duration/qualities, not found, or when the credit balance doesn't cover them (insufficient_funds). Returns {idempotency_key, total, queued, skipped: [{video_id, reason}]}; follow the progress with panda_get_hls_encryption_batches. To encrypt future uploads automatically use panda_set_new_uploads_encryption.

Finish an A/B test and declare a winner. PERMANENT — cannot be reversed.

End a live broadcast

Generate ONE AI package resource of a video — eBook, mind map or quiz — in one or more languages, with its settings and extra instructions (same as the dashboard: Video Settings → Panda AI). PAID: 1 credit per minute of video per language (minimum 1 min; a partial minute counts only past 1 s), e.g. a 10-minute video in 2 languages = 20 credits. On an active Gold/Enterprise plan the free daily AI quota covers the whole request while it lasts (1 use per request, checked before sending). Languages that already have this resource, or are still generating, are skipped (listed in skipped); the balance is checked before sending. The resource is ready in a few minutes; follow it with panda_get_ai_workflows. Returns {video_id, resource, from_lang, to_langs, skipped, gross_cost_credits, cost_credits, free_by_daily_quota, response}; response is the queued request (its id isn't a work id: the works show up in panda_get_ai_workflows once processed). To redo an existing one use panda_regenerate_ai_resource.

Generate subtitles for a video using Panda AI. Creates a transcription in the specified language. Costs credits based on video duration and tier.

Generate a presigned URL to upload a PDF/file to a Tutor AI assistant. Returns upload_url and file_id. After uploading, call panda_confirm_tutor_file_upload.