← Plugin catalog
Creativity

idea.ai

idea.ai v0.4.0

Video, images, audio and 3D

Create a free account to save this plugin.

From the developer

Declared capabilities

  • Image generation and editing
  • Video generation and editing
  • Speech, music and sound effects

Cost & access

Users require a paid idea.ai subscription to access the MCP tools. Subscriptions are obtained on the idea.ai platform, and generations consume coins from the connected idea.ai account. Costs depend on the selected model and generation settings.

Declared limitations

  • Publishing and ad buying are outside the exposed MCP tools. Explain that limitation and offer available asset delivery. Do not invoke any paid media operation to simulate publication, claim a post/ad was created, or attempt payment.
  • No character-training or persistent identity-registration tool was exposed. Explain reference-based reuse and a reusable brief as supported alternatives. Do not invoke any paid media operation as if it trained a model or claim an identity will persist across chats.
  • No topology editor, rigging tool, or manufacturing-certification tool was exposed. Explain which operations need other tooling. Do not generate a replacement as a substitute or falsely certify geometry quality.

Onboarding example

Help me create a visual with idea.ai.
Sources & dates

Developer declarations; not independently tested. Listing last checked Nov 16, 2026. Package observed Nov 16, 2026.

View package source →

Description

From the marketplace listing

Create and edit images, video clips, audio, and 3D assets with idea.ai. Twelve guided workflows help you maintain character consistency, create product campaigns, develop storyboards and video shots, transfer motion, make talking presenters, localize videos, adapt social layouts, produce audio, restore assets, develop 3D models, extract highlights, and create vector artwork concepts. Reuse reference assets and refine results through follow-up requests. Available models, controls, and output formats vary by workflow.

Language: English · Automatically detected from descriptions.

Changes

No changes recorded yet. Follow this plugin to keep track of future changes.

First seen Nov 16, 2026. Last seen Nov 16, 2026.

Files & skills

File archives

Plugin package20 files · 24.2 KBBrowse files →
Skill instructions
idea-ai-3d-assets2.67 KB

View saved version →

---
name: idea-ai-3d-assets
description: "Develop a 3D asset from a description or reference images with idea.ai, selecting supported mesh, material, and export options for its intended use."
---

# 3D asset development

Read [the shared MCP workflow](../../references/mcp-workflow.md) before calling tools. It defines discovery, file handling, cost authorization, waiting, and delivery for this skill.

## MCP operation

Use `create_3d_model` with the selected model and its supported format options. Omit files for text-to-3D; for image-to-3D, supply ready upload IDs or existing result URLs without inventing file roles.

## Define the asset

Establish the object's shape, distinguishing features, materials, intended use, and desired file format. Separate appearance from requirements such as scale, rigging, topology, game-engine readiness, or printing. Ask about those requirements when they determine whether generation alone can satisfy the request.

For reference-based work, choose complementary views of the same object. Do not treat conflicting designs as a consistent multiview reference. Create additional concept views only when requested or included in the approved budget.

## Inspect generation and export options

Hyper3D Gen2 (`hyper3d_gen2`) exposes `textTo3D` and `imageTo3D`; its inspected image mode accepts up to five images. It exposes `file_format` choices GLB, OBJ, USDZ, FBX, and STL, plus `material`, `mesh_mode`, `hd_texture`, and `seed` settings. Recheck current values before use.

Meshy 7.1 (`meshy_7_1`) and Meshy 7.1 Print (`meshy_7_1_print`) expose single-image generation with fewer options. A model name containing Print is not a printability certificate. Do not invent absent polygon-count, skeleton, retopology, or manufacturing controls.

## Inspect what can be verified

Review available previews for silhouette, proportions, missing parts, materials, and reference fidelity. Verify that an actual returned artifact matches the requested supported format before describing it as delivered. If geometry cannot be inspected, identify that limitation.

For completed GLB or glTF outputs, use the free `preview_3d` once with the existing generation ID when available; deliver the model URL alongside it. Other formats use their returned download URL. Do not generate another asset solely to obtain a preview. Call `quote_cost` for the actual request before generation even when get_model shows a standard base price.

Deliver the model and preview with the selected settings. Do not claim that the result is watertight, correctly scaled, rigged, production-ready, or printable without appropriate checks. Explain any remaining validation or editing step and the additional tooling it needs.
idea-ai-asset-restoration2.48 KB

View saved version →

---
name: idea-ai-asset-restoration
description: "Enhance or upscale existing images and video, or clean source audio, using idea.ai models selected for the source and requested improvement."
---

# Asset restoration

Read [the shared MCP workflow](../../references/mcp-workflow.md) before calling tools. It defines discovery, file handling, cost authorization, waiting, and delivery for this skill.

## MCP operation

Use `edit_image` for image enhancement, `create_video` for footage enhancement, and `create_audio` for audio cleanup. Upload and validate the source before pricing; request only the desired restoration operation.

## Assess the source and goal

Determine whether the user needs image upscaling, footage enhancement, frame-rate conversion, or audio cleanup. Use actual source metadata and inspect representative content when possible. Ask for a target resolution, frame rate, or loudness only when it affects the choice; avoid inventing detail that was not captured.

## Match the source to a model

Inspect current model constraints. Real-ESRGAN (`real_esrgan`) exposes `upscale_factor` and `output_format`, but its inspected source-image limit is 1024 by 1024 pixels. Topaz Proteus (`topaz_proteus`) exposes video `resolution` and `fps` with its own duration, dimension, and aspect-ratio limits.

VEED Clean Audio (`fal_veed_clean_audio_v1`) accepts either source video or source audio, with a combined maximum of one file; it exposes `strength`, `normalize_loudness`, `target_lufs`, and output format. Quote the selected source role with actual measured duration. Explain current reserve-and-settle guidance, including any source-role maximum reserved for URL-sourced audio, before spending. A quote is not automatically a hard spending cap. Cleaning a video's audio produces an audio asset, not necessarily a newly muxed video.

Reject an incompatible plan before upload or quoting. Use a supported alternative or a separately authorized preprocessing step rather than silently submitting a source outside the model's limits.

## Compare with the original

Assess halos, oversharpening, altered faces/textures, motion artifacts, unnatural interpolation, clipped sound, and excessive cleanup. Preserve the original. A larger file is not proof of added detail, and interpolation does not recover real captured frames.

Deliver the enhanced assets with actual returned metadata, selected settings, and any remaining defects. Reattaching cleaned audio or assembling outputs requires a tool that explicitly supports it.
idea-ai-audio-production2.57 KB

View saved version →

---
name: idea-ai-audio-production
description: "Create coordinated narration, music, and sound effects with idea.ai from a creative brief, with deliberate voice, timing, and cost choices."
---

# Audio production pack

Read [the shared MCP workflow](../../references/mcp-workflow.md) before calling tools. It defines discovery, file handling, cost authorization, waiting, and delivery for this skill.

## MCP operation

Use `create_audio` for each narration, music, effects, or cleanup asset. For uploaded sources, use measured upload metadata in `quote_cost` before approving a media-to-audio operation.

## Turn the brief into an audio plan

Identify the requested assets: narration, a music bed, sound effects, or a subset. Establish language, duration, mood, pace, instrumentation, loop requirements, and intended use. Keep an explicit asset list with one purpose and duration target per item.

## Inspect the relevant audio models

Discovery examples are ElevenLabs v3 (`eleven_v3`), ElevenLabs Music (`eleven_music_v1`), and ElevenLabs Sound Effects (`eleven_sound_effects_v1`). Inspect actual models before choosing options. Music exposes `duration_seconds` and `force_instrumental`; sound effects exposes `duration_seconds` and `loop`.

For speech, obtain the model's voice catalogue and real voice IDs through `list_voices`. Use facets to resolve missing preferences and offer a small selection instead of silently picking from hundreds of voices. Keep script wording distinct from voice direction.

Quote each asset using its actual prompt or structured `inputs` text/voice list and complete options. For structured dialogue, retain `inputs` when merging resolvedOptions; a separate prompt is optional. For prompt-priced speech, include the actual script rather than letting an omitted prompt select a maximum-length quote. Explain any reservation and settlement conditions. A revised script can change the price.

## Review and deliver the assets

Check spoken wording, pronunciation, pacing, requested duration, clipping, noise, musical direction, and loop seams where playback is available. For existing noisy media, VEED Clean Audio (`fal_veed_clean_audio_v1`) exposes normalization, strength, and loudness controls; treat cleanup as an additional scoped action.

Deliver separate, clearly named audio files with their purpose and timing notes. A general multitrack mixer is not exposed by the inspected tools. Do not claim that independently generated music, narration, and effects have been mixed or synchronized into a finished soundtrack unless an available additional tool actually performs and verifies that work.
idea-ai-character-consistency2.77 KB

View saved version →

---
name: idea-ai-character-consistency
description: "Create or edit a series of images with the same character using idea.ai, preserving defining features across scenes, poses, expressions, and outfits."
---

# Character consistency

Read [the shared MCP workflow](../../references/mcp-workflow.md) before calling tools. It defines discovery, file handling, cost authorization, waiting, and delivery for this skill.

## MCP operation

Use `create_image` for an initial text-only reference and `edit_image` for reference-based scenes and corrections. Keep the approved original URL or ready upload ID in every scene request.

## Establish the identity

Use an approved character reference as the source of truth. If references disagree, ask which controls the disputed feature. If no reference exists, write a brief and create one reference image within the authorized budget; get the character approved before producing the series.

Record the original reference ID or URL, visible defining features, proportions, distinctive marks, outfit, and rendering style. Keep requested changes in expression, wardrobe, setting, and lighting separate from identity. Do not invent hidden features or claim the brief persists into another chat.

## Choose reference controls

Inspect suitable models with `get_model`. Discovery examples include Kling V3 Omni (`kling_v3_omni_image`), Seedream 5 Pro (`seedream_5_pro`), FLUX.2 Pro (`flux_2_pro`), and Nano Banana 2.1 (`nano_banana_2_1`). Their inspected schemas support multiple reference/source images. Recheck any `aspectFit` rules and quote each affected reference with measured dimensions and the actual target options; a standard base price may not include fitting charges. Kling's named reference inputs require aliases; do not copy those roles onto another model.

Use the same approved original reference in each scene. No persistent character ID, character-training tool, or guaranteed identity lock was exposed in the inspected tools. Do not invent one or present a fixed seed as an identity guarantee.

## Generate and assess the set

Build each request from the stable brief plus the scene-specific changes. Keep the selected model and style consistent unless the user requests a change or a demonstrated limitation requires one.

Compare outputs with the original reference for facial structure, hair, marks, proportions, outfit, and style. Account for perspective, lighting, and intentional expression changes. Identify specific mismatches and repair only the affected scene, using a targeted edit when supported. Repeatedly using the newest output as the sole reference can accumulate drift.

Deliver the scene-ordered images, reusable brief, original reference identifier, and unresolved differences. Stop when the requested set is assessed or the agreed budget/retry limit is reached.
idea-ai-motion-transfer2.25 KB

View saved version →

---
name: idea-ai-motion-transfer
description: "Animate a supplied character or subject using motion from a reference video through idea.ai motion-control models."
---

# Motion transfer

Read [the shared MCP workflow](../../references/mcp-workflow.md) before calling tools. It defines discovery, file handling, cost authorization, waiting, and delivery for this skill.

## MCP operation

Use free `upload_media` with both motion input slots when the files are on the user’s device, resolve ready uploads and measured metadata, then quote and use `create_video`. Uploading the references does not start animation.

## Establish the two references

Identify the character/subject image and the motion video. Clarify whether the user wants the clip's movement, camera behavior, and original sound preserved; those are separate choices. Inspect the image and clip when available to describe what can be transferred and flag mismatched framing or visibility.

## Validate the model inputs

Inspect Kling V3 Motion Control (`kling_v3_motion_control`) or another available motion-control model. Its inspected schema requires paired `motionImage` and `motionVideo` roles, with a 3–10-second motion video. Validate current duration, format, image dimensions, and size limits before scheduling a generation.

Use the returned `character_orientation`, `keep_original_sound`, and `mode` choices where supported. Do not invent a skeleton, pose track, or character ID. Model controls may not isolate every aspect of motion from camera behavior.

For user-owned files, declare both required inputs in one authorized upload request. For assets already generated through the MCP, reuse their URLs with the correct roles.

## Assess the result

Review movement timing, body/subject proportions, identity, framing, unintended distortions, and the requested sound treatment. Do not claim frame-accurate motion capture or perfect identity preservation from a completed status alone.

If the reference clip is outside the model's limits, ask for a suitable excerpt or use separately authorized trimming tools that are actually available. Do not silently submit unsupported media or repeatedly retry it.

Deliver the result with the source references and a concise account of any motion or identity differences that remain.
idea-ai-product-campaign2.46 KB

View saved version →

---
name: idea-ai-product-campaign
description: "Create coordinated product campaign images with idea.ai from product references, including hero images, lifestyle scenes, detail shots, and social variants."
---

# Product campaign kit

Read [the shared MCP workflow](../../references/mcp-workflow.md) before calling tools. It defines discovery, file handling, cost authorization, waiting, and delivery for this skill.

## MCP operation

Use `edit_image` for product-reference scenes, focused corrections, resizing, and outpainting; use `create_image` only for requested text-only concepts. Quote every supplied reference input, not just the output resolution.

## Define the campaign

Establish the product, audience, campaign message, intended placements, and requested deliverables. Reuse supplied brand choices. Ask only for missing facts that affect the assets, such as packaging details that must be legible or a claim that needs the user's exact wording.

Treat product geometry, label text, colors, and essential accessories as invariants. Distinguish the product reference from style or setting references. Propose a small scene plan with the purpose and format of each asset before pricing the batch.

## Select a reference-based image workflow

Inspect available image models. Discovery examples include Seedream 5 Pro (`seedream_5_pro`), Nano Banana 2.1 (`nano_banana_2_1`), and Kling V3 Omni (`kling_v3_omni_image`) for multi-image work. Ideogram 4.5 Precise Edit (`ideogram_v4_5_precise_edit`) exposes a rectangular edit region for a focused correction.

Create one representative campaign image first when the visual direction is unsettled. Use an existing approved direction directly. Keep product and style references stable across scenes, changing only scene-specific composition, props, action, or framing.

## Review and deliver

Check each result for product shape, proportions, packaging, readable text, brand colors, misleading additions, and placement requirements. Reference inputs do not guarantee exact logo or packaging reproduction. If exact artwork cannot be preserved, identify the affected asset and propose a supported correction or later layout step.

Resize or outpaint approved images when that meets the format requirement without another redesign. Do not add video, new claims, or extra variants outside the requested campaign and budget.

Deliver a labeled asset set with its intended placement and dimensions, approved creative direction, references, and any corrections still needed.
idea-ai-social-formats2.13 KB

View saved version →

---
name: idea-ai-social-formats
description: "Adapt an approved image into multiple social or advertising layouts using idea.ai resizing and outpainting controls."
---

# Social image formats

Read [the shared MCP workflow](../../references/mcp-workflow.md) before calling tools. It defines discovery, file handling, cost authorization, waiting, and delivery for this skill.

## MCP operation

Use `edit_image` with the selected resize or outpaint model. A local source can be uploaded and measured for free before pricing; the adaptation itself is a paid operation.

## Establish the format plan

Use the approved source image and the user's target placements or exact dimensions. Confirm focal subjects, text/logos that must survive, and areas reserved for copy. When dimensions are unspecified, propose aspect ratios as creative choices; do not invent current platform advertising requirements.

## Choose resize versus outpaint

Inspect Smart Resize (`fal_smart_resize`) for an available `targetSize`. Inspect Recraft V3 Outpaint (`recraft_v3_outpaint`) when the image needs additional canvas; it exposes independent expansion directions and `zoom_out_percentage`.

Choose the least disruptive supported operation. Resizing a composition and generating new surrounding content have different effects, so describe which is planned. Validate source dimensions and size limits. Price each output and keep its relationship to the original reference clear.

## Review the adaptations

Check focal-subject visibility, crop boundaries, stretched proportions, text legibility, logo integrity, new visual artifacts, and usable copy space. Compare new surrounding content with the source's lighting, perspective, and style. Keep accepted variants and repair only failed ones.

Do not silently replace exact brand text or treat generated text as an approved final layout. If a placement needs accurate typography or a layout operation not exposed by the tools, identify that finishing step.

Deliver a labeled set with actual returned dimensions and intended placement. These tools create image assets; they do not publish posts, configure ad campaigns, or certify platform approval.
idea-ai-storyboard-video2.43 KB

View saved version →

---
name: idea-ai-storyboard-video
description: "Turn a creative brief into a storyboard, approved keyframes, and individual generated video shots with idea.ai."
---

# Storyboard to video clips

Read [the shared MCP workflow](../../references/mcp-workflow.md) before calling tools. It defines discovery, file handling, cost authorization, waiting, and delivery for this skill.

## MCP operation

Use `create_image` or `edit_image` for keyframes, then `create_video` for each approved shot or extension. The operation selects text versus media mode from the supplied files; it does not take a `modality` parameter.

## Plan the shots

Translate the brief into a shot list with action, subject, framing, camera motion, intended duration, aspect ratio, and audio requirements. Preserve approved character/product references and continuity. Distinguish an individual clip from an assembled finished film.

Create or reuse keyframes before animating when they materially improve control. Get approval for an unsettled visual direction before generating the remaining shots. Include keyframe creation and each video shot in the budget.

## Choose valid video inputs

Inspect video models with `get_model`. Seedance 2.5 (`seedance_v2_5`) supports either first/last-frame inputs or named image/audio/video references; its inspected cross-role rules make those groups mutually exclusive. A last frame requires a first frame. Runway Gen-4.5 (`runway_gen4_5`) exposes a first-frame input.

Use the chosen model's actual duration, resolution, and aspect-ratio controls. Do not combine incompatible input groups or assume that adding sound references creates a complete mixed soundtrack. Seedance's Extend variant (`seedance_v2_5_video_extended`) has a combined source-plus-extension duration limit; inspect it before proposing an extension.

## Generate and review shots

Keep each prompt focused on the shot's visible action and camera behavior. Reuse approved source images by URL. Review subject identity, product fidelity, continuity, requested motion, framing, timing, and artifacts. Revise the affected shot rather than regenerating the entire storyboard.

Deliver numbered clips with the shot list, durations, keyframes, and editing notes. The exposed tools do not include a general timeline-assembly or editing-project export tool. If a finished edited film is requested, explain which assembly step needs additional tooling instead of claiming that independent clips are a completed edit.
idea-ai-talking-presenter2.34 KB

View saved version →

---
name: idea-ai-talking-presenter
description: "Create a talking presenter video with idea.ai by combining an approved portrait, script, selected voice, and generated narration."
---

# Talking presenter

Read [the shared MCP workflow](../../references/mcp-workflow.md) before calling tools. It defines discovery, file handling, cost authorization, waiting, and delivery for this skill.

## MCP operation

Use `create_audio` for approved narration and `create_video` for the presenter. Reuse the generated narration URL and upload the portrait through the free upload flow when needed.

## Prepare the presenter and script

Use the user's approved portrait and intended script. Establish language, voice preferences, delivery, target duration, and video format. Preserve names, numbers, and factual claims; get user wording for unresolved claims rather than inventing endorsements.

If the user already supplies suitable narration, reuse it instead of generating replacement audio. Otherwise inspect a speech model such as ElevenLabs v3 (`eleven_v3`). Its `inputs` contain text and a `voice.voice_id`; obtain that ID from the model's actual `voiceCatalog` through `list_voices`.

Use voice facets to help resolve unspecified preferences, then show a small relevant selection. Never invent voice IDs or reuse an ID from a different catalogue. Price the narration and presenter generation as separate paid actions.

## Generate narration, then the presenter

Review or obtain approval for narration when pronunciation and delivery matter before spending on video. Preserve the accepted audio output URL.

Inspect HeyGen Avatar 5 (`heygen_avatar_5`) or another suitable available model. Its inspected contract requires `sourceImage` and `sourceAudio`; the audio limit is 1–120 seconds. Use actual aspect-ratio and resolution options, and check that the portrait and narration meet current file constraints.

## Review and deliver

Assess spoken wording, pronunciation, pacing, lip synchronization, face stability, framing, and duration. Mark aspects that cannot be played or inspected as unverified. Correct audio issues before rebuilding an otherwise acceptable video.

Deliver the presenter video, approved script, and narration asset where useful. Do not promise a reusable trained avatar, voice cloning, or scene editing unless the chosen tool explicitly supports it and the user requested it.
idea-ai-vector-artwork2.3 KB

View saved version →

---
name: idea-ai-vector-artwork
description: "Develop related icons or illustration concepts with idea.ai\u2019s SVG-oriented generation model, verifying actual output formats before claiming editable vectors."
---

# Vector artwork kit

Read [the shared MCP workflow](../../references/mcp-workflow.md) before calling tools. It defines discovery, file handling, cost authorization, waiting, and delivery for this skill.

## MCP operation

Use `create_image` for text-to-image artwork concepts. Do not route raster-to-vector requests to `edit_image` without a model whose inspected capabilities actually support that operation.

## Establish the visual system

Define the required icons or illustrations, their meanings, intended sizes, palette, stroke treatment, fill style, level of detail, and background treatment. Identify which details must remain recognizable at small sizes.

Use an approved sample or create one representative design first when the direction is unsettled. Translate the chosen direction into a concise art-direction brief for the remaining items. Do not assume that a model can ingest a style reference unless its current modality explicitly accepts one.

## Inspect the SVG-oriented model

The discovered catalogue includes Recraft V4 SVG (`recraft_v4_svg`) with `textToImage` and an `aspect_ratio` option. Its inspected schema labels the output type as `image` and does not expose an SVG path editor or a reference-image input. Verify the actual returned artifact before claiming SVG export or editability.

If the user needs vectorization of an existing raster image, search the live catalogue for that specific capability. Do not relabel fresh text-to-image generation as faithful raster-to-vector conversion.

## Review the set

Compare silhouette, visual weight, spacing, stroke treatment, palette, and semantic clarity across assets. Inspect small-size legibility where the host can display the results. Preserve approved items and revise the inconsistent ones within budget.

Deliver the returned artwork, its verified file type, and the reusable style brief. If an output is a raster preview or its vector structure cannot be checked, state that limitation. Do not promise editable layers, outlined fonts, production-ready paths, or a complete design-system component library without corresponding verified artifacts.
idea-ai-video-highlights2.25 KB

View saved version →

---
name: idea-ai-video-highlights
description: "Extract highlights from longer footage with idea.ai using an editorial scoring brief and requested clip durations."
---

# Highlight clips

Read [the shared MCP workflow](../../references/mcp-workflow.md) before calling tools. It defines discovery, file handling, cost authorization, waiting, and delivery for this skill.

## MCP operation

Use `create_video` for highlight clipping after the free source upload is ready and its measured duration has been quoted. Optional transcription uses a separate, authorized `extract_text_from_media` operation on a model supporting `mediaToText`.

## Define what makes a highlight

Identify the source footage, audience, desired number of clips, duration targets, and editorial criteria. Use a supplied transcript or timecodes when available, but do not claim to have watched or transcribed footage the host cannot inspect.

Write a concrete scoring brief: the moments to favor, necessary context, and content to avoid cutting mid-action. Keep extraction separate from captioning, reframing, soundtrack changes, or publishing.

## Validate the clipping model

Inspect BytePlus Highlight Clipping (`byteplus_video_highlights_v1`). Its inspected contract accepts source video from 10 seconds to three hours and up to five `targetDurations`, each 1–600 seconds. It also exposes `scoringPrompt`; its only named preset is `football`, so do not invent other preset values or assume that preset fits every genre.

Check current file-size and format limits. Quote using the actual source duration and requested `targetDurations`. Use the free upload flow to obtain measured duration before quoting; do not guess a clip's length for billing.

## Review the selected moments

Check that returned clips match the scoring intent, include enough context, begin and end coherently, and meet the requested durations. Report when semantic relevance cannot be reviewed. If the result misses the brief, explain the specific mismatch before an authorized revision.

Deliver the actual clips and returned timing information. Do not fabricate source timecodes, assume multiple outputs from a successful status, or claim social publication. Captioning and format adaptation are optional additional steps with their own tools and costs.
idea-ai-video-localization2.39 KB

View saved version →

---
name: idea-ai-video-localization
description: "Create dubbed or subtitled language versions of an existing video with idea.ai while preserving approved terminology and presentation."
---

# Video localization

Read [the shared MCP workflow](../../references/mcp-workflow.md) before calling tools. It defines discovery, file handling, cost authorization, waiting, and delivery for this skill.

## MCP operation

Use `create_video` separately for dubbing and subtitles. If transcription is requested, discover a compatible `mediaToText` model and price `extract_text_from_media` as a separate paid operation; do not silently transcribe just to inspect the source.

## Define the language versions

Identify the source video, source language, target languages, audience, pronunciation needs, and any supplied script, glossary, or SRT. Keep proper names, numbers, product terminology, and approved claims consistent. Separate translation, dubbing, and subtitle styling so each requested operation is explicit.

## Inspect dubbing and subtitle controls

Inspect VEED Dubbing Pro (`veed_dubbing_pro_v1`) or another available dubbing model. Its inspected schema exposes `source_language`, `target_language`, and `voice_cloning_strength`; use only returned language values. Do not assume global plugin availability means that a model supports every language.

Inspect VEED Subtitles (`fal_veed_subtitles_v1`) for captioning. Its contract requires a subtitle `preset` and supports `language`, optional `srt_content`, and style customization. Preserve user-supplied timing and wording unless an adjustment is requested. Confirm current file duration and size limits for each step.

Quote each language version and each subsequent subtitle operation separately. Where an output feeds the next operation, use its generated URL rather than asking for another upload.

## Review the localized versions

Check terminology, pronunciation, translation meaning, timing, voice treatment, subtitle contrast, line breaks, safe placement, and overflow. If the host cannot play audio or inspect target-language content adequately, describe that limit and request a fluent review instead of declaring linguistic accuracy.

Deliver clearly labeled language versions and list the original and translated wording when available. Do not claim to export an editable subtitle file merely because subtitles were burned into a returned video; verify the actual output artifacts.

Release notes

Updates quoting for actual prompts, complete options, reference-fitting surcharges and reserve-and-settle audio pricing; adds free GLB/glTF previews; refreshes upload/session guidance, model-rule handling, troubleshooting, and review cases against the 13 November MCP. Retains all twelve skills, branding, direct privacy link, and worldwide availability.

Declared in the saved package. Remote tools may change independently.

Package details

Publisher declarations from the archived package. These are separate from our research and the live service's terms.

Package author
idea.ai
Declared availability
No country restrictions declaredDeclared regions; live availability may differ.
Commerce declaration
Supports commerceThis does not establish whether access is free or paid.
Review scenarios
5 positive · 3 negativeScenario counts, not test results.

Declared capabilities

  • Image generation and editing
  • Video generation and editing
  • Speech, music and sound effects
  • 3D asset generation

Package observed Nov 16, 2026.

Technical details
First seen
Nov 16, 2026 · 18:00 UTC
Last seen
Nov 16, 2026 · 18:00 UTC
Collection status
Collected

plugin_asdk_app_6aee1baa4d8c8191aad5148cb8dd31fe

Download plugin data (JSON)

Plugin details: freshly prepared. Prepared . Refreshed when plugin data changes or after 6 hours. Your account and Follow status are live.