--- name: toon-turbo description: Generate a 15 s cartoon episode from one 3×3 storyboard on H3 Max Turbo image-to-video with the model's own voices and sound — the board as the first frame only, 480P, 15 s, prompt expansion off, no end frame, no target audio, the prompt that keeps the board off screen — then cut the board flash. --- # Animate a cartoon storyboard with native sound FlashBoards user skill, version 1.2.3 (2026-10-13). On the board, read these guides with `list_skills` and `get_skill` when the assistant exposes them; otherwise use the hosted index through an available read-only retrieval tool. Use that runtime’s actual model discovery, current page context and guarded board actions for execution. Keep native readiness, approval and cost gates; do not claim a guide was read when retrieval is unavailable. Read related guides with `get_skill({skillId:""})` or the [hosted index](https://pub-78da82d51ed14147ac554d38094b0c0b.r2.dev/user-skills/1.2.3/index.html). Reading a guide does not start or authorize a paid generation. Read `toon` for the shared rules. > **Quality route:** Seedance 2.5 (`seedance-2-5`) with the board as @Image1, up to 30 s a call and `sound: true`, does this job much better; the H3 method below is the low-cost route — quote both. ## The call `generate_video` with `minimax-h3-max-turbo` · `firstFrameUrl: ` · `duration: 15` · `resolution: "480P"` · `promptExpansion: "disabled"`. **No `endFrameUrl`, no `targetAudioUrl`.** ## The prompt (prose, in this order) 1. `A 15-second animated short, "{title}", in the style of {style}. Expressive, funny, heartfelt cartoon acting: big emotions on every face, squash and stretch, snappy comic timing. 16:9, nine shots with cuts at the given times.` 2. `The given first image is NOT a shot: it is the storyboard for this film, nine numbered frames in three rows of three on black. It never appears on screen; the film starts directly inside frame 1, and every shot looks exactly like its storyboard frame enlarged to the full screen. The screen is never split into a grid.` 3. The characters with **voices in words**: `{NAME} … a warm, low, playful voice. {SIDEKICK} … a tiny, high, squeaky cartoon voice, fast and excitable.` 4. Nine lines `Shot k (frame k, a–b s): {action with emotion}. {Who}: "{line}"` — about 1.7 s a shot. 5. `Sound: generated with the picture — the voices, {music and sounds of the style}, and cartoon foley for every action, all quieter than the voices. Each character speaks only their own lines, lips in sync. No subtitles, no text, no live action.` ## Cut the board flash The board shows at the start (1–7 frames in the tests; other Turbo takes held a board up to about 1.6 s) and never comes back. `detect_video_cuts` on the episode → `trim_video` with `startSeconds` = the first cut plus one frame, `snapToFrames: true`. Never claim "no flash" without this step. The trim's `generationId` is the finished episode: check it (`describe_media`, `transcribe_media`), show it (`display_generation`) and place it on the board (`add_media_to_board`). ## What to expect All lines spoken, roughly on time; sometimes an extra word or a sound that is not what was asked (a hiccup heard as a raspberry, a sneeze as a scream); a comic-book style may add a speech bubble despite "no text". ## Check `transcribe_media` the episode against the nine lines; `extract_video_frame` at the first second and `describe_media` "Is any part of the storyboard grid visible? Any speech bubble or text?" ## Execute through MCP or on the board Use the person's FlashBoards account; never ask for a personal provider key or run the source's local scripts. Discover `get_account`, `list_generation_models` and the tools of this client first: a published guide does not prove a feature is deployed. **Headless, no open board.** Quote with `estimate_generation_cost` (skill models: `estimate_skill_model`), then run `generate_image`, `generate_video`, `generate_audio` or `run_skill_model` with one stable `generationAttemptId` per logical attempt. Pass `maxCostUsd` only when the current operation and selected model support it; otherwise use the quoted cost and the person's explicit approval with the supported controls. Never silently ignore an unsupported spending cap; make one `get_generation` check after `retryAfterSeconds`. Pass the person's own results by `generationId`: images in `referenceGenerationIds`, `firstFrameUrl` and `endFrameUrl`, audio in `referenceAudioUrls` or `targetAudioUrl`, videos in `referenceVideoGenerationIds`. They are read on the server; signed result links do not work as public URLs. Every `generationId` a tool returns stays valid: a later read of the same result gives a different string, and both work. Film frames and gallery pictures go in by `previewHandle`: `referencePreviewHandles` of the generation tools, a `{previewHandle}` source of `arrange_images`, `crop_image` and `pad_image`, and `describe_media`. New files come from `show_media_upload_picker` as receipts. The person's character comes in as its sheet, by `generationId` or as an upload; there is no search by name. If the person names a character without the sheet, ask for it or make one with `character-sheet`; do not scan recent results for it. Free server steps: `trim_video`, `concat_videos`, `conform_video`, `replace_video_audio`, `extract_video_frame`, `extract_video_audio`, `detect_video_cuts`, `crop_image`, `pad_image`, `arrange_images`, `cut_audio_span`, `concat_audio_tracks`, `mix_audio_tracks`, `fit_audio_duration`, `add_audio_reverb`. Check every result with `describe_media` (a question about an image; `model`, `mode` and `sourceRange` only for a video) and `transcribe_media` for speech. Both checks are paid: `describe_media` costs a fraction of a cent for an image and about 2–4 ¢ for a short video (more for a long one), `transcribe_media` under 1 ¢ a minute — count the checks you plan in the price you name before the first paid step. `describe_media` is not reliable about sound: it misses effects mixed under music and can hear voices or instruments that are not there. Check speech with `transcribe_media` and ask the person to listen for effects and music. Never repay an uncertain submission; reuse an attempt ID only for the identical request. Make each new `requestId` or `generationAttemptId` unique, for example the task, the date and a short random suffix: an ID used before, even in another chat, replays that earlier request or answers `REQUEST_ID_CONFLICT`. **On the board.** Inspect with `list_board_sessions` and `get_board_snapshot` and carry the same `sessionId` and a fresh `activeBoardId` as `expectedBoardId`. Native cards: `execute_board_action` (`listNativeModels`, `setModel`), `prepare_board_generation` with ordered board items or owned outputs, then one `generate_on_board` within the authorized budget. Board media tools: `list_media_tools` → `start_media_tool` → `get_media_tool_run`. Put headless results on a board with `add_media_to_board`. Keep mandatory safety settings and the live limits of each model. Prices, timings, endpoints and "free retry" claims in the sources are historical, not FlashBoards contracts. If a step this guide needs is not available or is refused (a tool error, `audio_not_configured`, a missing model or input), keep the finished assets, tell the person which step is blocked and why, and ask how to go on. A single generation that ends `failed` is not a blocked step: submit it once more with a new `generationAttemptId` (reworded if it may have hit the content checker), and stop to ask only if it fails again. A failed attempt is not always refunded, so the retry may be paid again and `maxCostUsd` caps each request on its own: count both against the budget the person approved. Never swap in another route on your own: no image model redrawing a layout or a frame, no `describe_media` in place of the frames it should check, no clip generated only to take its sound, no picture drawn where the guide takes a film frame. ## Source and related guides - [Original Learn guide](https://flashboards-h01.vercel.app/learn/formats-and-exhibition/ai-cartoon/skills/toon-turbo.md) - Updated from the owner's skill sources of 2026-10-11. Read: `toon`, `toon-storyboard`, `upscale-video-final`. Source experiments and demo materials are historical; use the person's own approved media.