---
name: musicvideo
description: Route an AI music video on a whole track starring the person's character — one film as the world, a linear three-act story, every face replaced, H3 Max Reference to Video in parts of up to 15 s with eight shots, transitions on the beat and lip-sync — on a low-cost H3 route or the Seedance 2.5 quality route.
---
# AI music video on a whole track

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:"<id>"})` 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.

Work for the person's own character and track. Slots in every musicvideo guide: {character} — the person's character (a story may have more than one person), {face board} — the five-angle face board of {character}, {look sheet} — the costume and prop sheet, {track}, {film}, {act}. Values in [brackets] are examples, not defaults.

## Entry level — the quick route first

Make everything first on the cheap route: pictures on GPT Image 2.5 Flare 2K (`gpt-image-25-flare`) at `quality: "low"`, video on H3 Max Turbo (`minimax-h3-max-turbo`) 480P from a fresh start frame, every shot with `targetAudioUrl` = that piece of the track. After a result the person likes: a Seedance 2.5 re-shoot or a video enhancement only on their pick.

## References first — offer them in the first reply

Offer to look at references together ("Show me references" / "I have my own" / "Skip"): the FlashBoards gallery for the track's mood, light and palette; three film worlds that fit the story (`search_movie_frames` with the story or the mood as `query`); optionally `vidiq_research` with `tool: "youtube_search"` for "<genre> music video". The pick sets the look and the film. Show at most three picks, one line each.

## The method

0. **Cast first.** The person's {character} is the lead. If the chosen {film} has a second main role, ask who plays it: another of their characters, an invented face, or removed. Never cast a demo character.
1. **The track** → lyrics with word times, style, the measured beat grid, parts of up to 15 s cut on a beat at a vocal pause → `musicvideo-track`.
2. **One film** whose story fits {track}; a **linear story in three acts** (joy → turn → catastrophe or ending); frames for every story beat → `musicvideo-film-scenes`.
3. **Every face replaced**: the lead → {character}, other main roles as cast, everyone else → invented faces; a new costume or prop is a {look sheet} first → `musicvideo-replace`.
4. **Video**: H3 Max Reference to Video, 16:9, 768P; Image 1 = {face board}, Image 2 = {look sheet}, then the frames; eight shots a part, cuts on beats, a different transition on every cut; light, action, acting, head movement and lip-sync written for every shot; all parts started together → `musicvideo-shots`.
5. **Edit**: trim each part to its length, join, lay the original track; one final enhancement → `musicvideo-edit`.

Write every prompt fresh for this track and story.

## Two routes — offer both with their current quotes

| Route | Model | When |
|---|---|---|
| Low cost | H3 Max Reference to Video (or Turbo), 480P–768P | drafts, many takes, a tight budget |
| Quality | Seedance 2.5 (`seedance-2-5`): pictures as @Image1…, the part of the track as @Audio1, up to 30 s a call | the final cut, when the look matters |

## Classify

| The job | Go to |
|---|---|
| Lyrics, style, tempo, where to cut the track | `musicvideo-track` |
| Choose the film, find the scenes and frames | `musicvideo-film-scenes` |
| Put the character into the frames, remove the actors | `musicvideo-replace` |
| Write the prompts and generate the parts | `musicvideo-shots` |
| Assemble, sound, enhance | `musicvideo-edit` |
| The finished video: will it work before posting | `viral-score` |
| Ready to post: versions per platform, the platform checks, the AI label and a caption | `viral-publish` |

## What was tried and dropped

| Approach | Why dropped |
|---|---|
| A choppy "fever dream" of 12 cuts a part | no story |
| A story with invented locations and friends | the outfit jumps between characters, no film feel |
| Scenes from three different films | not one world |
| Turbo extending a video, a frame per shot | only a still frame starts each shot |
| A selfie reel tied to the frames | the camera copies the film framing; a frontal face reference freezes the head |

## Rules

1. **One film, one linear story.** Supporting characters only as background.
2. **No actor's face on screen**, not even an extra's — check with crops.
3. **Props and costumes as pictures**, never as words (a look sheet → the frame edit → Image 2).
4. **Blind prompts**: picture roles only; the expression of a reference frame may be named.
5. **A five-angle face board as Image 1**, aspect 0.4–2.5 (two rows).
6. **Never mention phones** — the model draws them.
7. Never reuse another run's files, prompts, faces, frames or story for a person.

## 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-music-video/skills/musicvideo.md)
- Updated from the owner's skill sources of 2026-10-11.

Read: `musicvideo-track`, `musicvideo-film-scenes`, `musicvideo-replace`, `musicvideo-shots`, `musicvideo-edit`, `character-sheet`. Source experiments and demo materials are historical; use the person's own approved media.