Magnific

Show aspect-ratio picker when ratios are vague or explicitly requested; otherwise call `design_auto_resize`. Never call twice.

design_auto_resize_show

Filterable gallery widget (image/video/audio). Use instead of `creations_search` when user wants to browse their library.

creations_list

Reframe camera around subject. Defaults: rotate=45, vertical=0, closeup=5.

images_change_camera

Voice changer (ElevenLabs speech-to-speech): re-speaks an existing audio recording with a different catalog voice, preserving the original performance (timing, delivery, emotion). Get `voiceId` from `audio_voices_list` or `audio_voices_show`.

audio_voice_change

Re-shoots the clip from a different camera position around the same subject: `rotate` swings around it, `vertical` moves above or below it, `closeup` pushes in. Regenerates the footage, so it is not a crop — reframing without new pixels is `video_crop`. The still-image equivalent is `images_change_camera`. Then `creations_show`.

video_camera_angle

Grades a clip, either with a catalog LUT (`lutId` from `video_luts_list`, optionally softened with `intensity`) or with manual `adjustments`. Pass at least one of the two; both together apply the LUT and then the adjustments. Matching another clip's look instead → `video_color_transfer`. Max 20s / 200 MB. Requires a paid plan. Then `creations_show`.

video_color_grade

Add a comment (or reply) to a user-owned creation.

creations_comment

Rebuild hidden geometry of Tripo-segmented parts. Requires a completed models3d_segment result; arbitrary meshes cannot be completed.

models3d_complete

Concatenate completed video creations into one MP4. Assembles multi-clip plans from `video_plan`. Audio from each clip; no external audio bed. Returns queued creation.

video_concatenate

Charges and dubs from a ready preview. `segments` carries the user's corrections (id + voiceText/captionText per line); omit it to keep the preview as transcribed. `videoUrl`, `targetLanguage` and the options must match the preview. Queued: then `creations_show` / `creations_wait`.

video_dubbing_confirm

Trace raster creation into SVG. New vector from prompt: `images_generate_svg`.

images_to_svg

Convert Freepik stock item → Pikaso creation. Use after user selects from stock_show.

stock_to_creation

SDR→HDR via Topaz Hyperion 2.5. Keeps source res/fps. SDR input only; max 9000 frames / 3840×3840. Not an upscale — use `video_upscale`. Then `creations_show`.

video_hdr

Save a Space workflow as a reusable flow. Walks the graph connected to `startNodeId` and works out which nodes the runner fills in and which return results. `dryRun` shows that choice without creating anything. The flow is private to its owner.

flows_create

Create folder/project. No `parentReference`: workspace root. `type` defaults: project at root, folder when nested.

folders_create

Create a reusable library asset (character/product/location) from 1-6 images. Use the returned numeric `id` in generation refs (same id Spaces uses). No LoRA training.

library_create

Create a custom project tag (not a review status). Same as the feed footer: owner/admin/editor (`canCreate`). Pass projectReference from folders_list (project or folder ref by name — folder refs resolve to root project; UI folder irrelevant). Statuses already exist — never create those. On general feeds without a named project, ask which project unless onlyProjects shows a single project or only project_default. On duplicate/limit errors reuse existing — do not retry.

tags_create

Create empty Space. Share `space.webUrl`; only call `spaces_show` when inline preview is requested.

spaces_create

Tag/status vocabulary for filtering creations, and whether this account has tags. Feed the names to `creations_search`.

creations_tags

The video counterpart of `images_crop`: reframes a completed video creation to a new aspect ratio via Magnific Video Resizer (outpaints/crops as needed, does not simply letterbox). Costs credits. Optionally bill/render only a trimmed window of the source. Returns a new queued video creation; the source is untouched.

video_crop

Crop to `aspectRatio`: center by default, or `auto=true` for AI focal-point crop that keeps the subject. Pixels: `images_resize`. AI upscale: `images_upscale`. Ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9.

images_crop

Cut a completed video creation to a time range (free, no AI). Returns a new queued video creation; the source is untouched. End time is clamped to the video duration. Chain outputs into `video_concatenate` to re-assemble.

video_cut

Move a folder and its files to trash.

folders_delete

Permanently delete a library asset you can manage (`manage: true` in `library_list`, which includes team-managed assets you do not own) by numeric `id`. Deleting an original also deletes its variants; deleting a variant deletes only that variant. Irreversible.

library_delete

Delete a custom tag (or hide a review status for this project). Owner/admin only. Pass projectReference from folders_list (any project/folder by name — UI folder irrelevant). Address by name or id from tags_list. Removes assignments on creations.

tags_delete

Completed creation in an editor-native format (ProRes/DNxHR/hvc1 video, 16-bit PNG/TIFF or layered PSD image, WAV audio), optionally capped at 720p/1080p for video. Video and audio renders carry provenance metadata (creation id, model, prompt, date). Free; the render runs once and is stored. `ready` → download `url`; `processing` → call again after `poll_after_seconds`; `failed` → read `reason`, pass `retry=true` only if it can succeed.

creations_deliver

Estimates a DEPTH MAP of an image (Depth Anything 3): near is bright, far is dark. `colormap` grayscale (default) | inferno | viridis | turbo tints it for viewing. Useful as a control image or for parallax/3D effects. Surface maps (normal, roughness…) are `images_pbr_maps`. Then `creations_show`.

images_depth_map

Signed download URL for a stock item. Pass folder_reference to also save as a creation (not for 3d). type=3d converts to GLB asynchronously: `status` is `processing` with `retryAfterSeconds` until it is `ready`; repeat the same call.

stock_download

Edit a library asset you can manage (`manage: true` in `library_list`, which includes team-managed assets you do not own) — character/product/location — by numeric `id`. Partial update: send only fields to change. Optionally replace `cover` and/or `images` (reference set). No LoRA/variants/sheet regen.

library_edit

External MCP only. Start headless Space edit. Poll `spaces_edit_status` until allTerminal, then verify with `spaces_state`.

spaces_edit

AI skin enhancer. faithful preserves identity; creative reinterprets; flexible uses presets. Defaults: faithful, sharpen=0, smartGrain=0.

images_skin_enhancer

AI outpaint to `aspectRatio`: keeps the original and generates new surroundings, anchoring the subject automatically. Crop instead (no new pixels): `images_crop`. Ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9.

images_expand

Continues a clip past its last frame, generating `durationSeconds` of NEW footage that carries on from it. Use `prompt` to say what should happen next; omit it to let the model continue on its own. To join clips you already have, use `video_concatenate`; to change the existing footage, `video_modify`. Then `creations_show`.

video_extend

Extract the audio track of a completed video creation as MP3 (free, no AI). Returns a new queued audio creation; the source video is untouched.

video_extract_audio

Extract still frames from a completed video creation at given timestamps (free, no AI). Pass the timestamp "last" to grab the final frame — the image to send as keyframes.start when extending a video whose source has no stored last-frame (mediaCollection has no type:frame, index:-1 item). Returns one queued IMAGE creation per timestamp; the source video is untouched.

video_extract_frames

Step 2 after PUT from `creations_request_upload`: convert temp path(s) to creations. SVG <=10MB, raster images <=25MB, audio <=50MB, videos <=200MB.

creations_finalize_upload

Image-to-3D GLB. Upload external images first. Rig with `models3d_rig`, then animate with `models3d_animate`.

models3d_generate

Text-to-3D GLB from a prompt. Tripo supports textured models; Meshy returns a bare geometry preview. No source image. For image-to-3D use `models3d_generate`.

models3d_text_generate

Generate images, or rework one via references. NOT pixel-preserving: an edit that must keep the rest intact routes to a dedicated tool first — sharpness/quality: `images_upscale`; free space/extend canvas/new ratio keeping content: `images_expand`; one region: `images_retouch`; crop/exact pixels: `images_crop`/`images_resize`. No refs=TTI. references[] (max 12; see field docs). Output is opaque unless `transparentBackground` is set on a model that supports it; otherwise chain `images_remove_background` after. Defaults: mode=auto, ratio=1:1, count<=8. resolution/quality/variant/tier per images_models_list. UI clients: after generating, MUST call `creations_show` with all identifiers; never stop at links.

images_generate

Generate image-variation grid; each tile becomes its own creation (creations_wait → results.tiles). Modes: angles|demographics|expressions|age|storyboard|custom. Defaults: angles, 3x3, 1:1, 4k.

images_variations