--- name: music-after description: What to do with a finished take — pick a take, stems (vocal + instrumental by default, multi-stem only on request), a longer version with Suno V6 Audio Extend, fixed words or style as a new round, square cover art, and a music video. --- # After the take 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 `music` for the shared rules. {track} is a take made here: its `generationId`. ## What next After they pick a take, ask what next (several may be picked): "Stems — vocal + beat" · "Make it longer" · "Fix words or style" · "Cover art" · "Music video". Do the picked ones in this order. | Pick | Do | |---|---| | Stems | `run_skill_model` with `suno-vocal-separation` and `audio_url` = {track} → the vocal and the instrumental. **Only these two unless they ask** for drums, bass and the rest: then `suno-multi-stems` — each run is paid again, never "just in case". | | Longer | `run_skill_model` with `suno-v6-extend`: `upload_url` = {track}, `continue_at` = the second to continue from (for example the end of the last chorus, strictly inside the track), `style`, and `lyrics` with the new lines (a verse or the last chorus and an outro); two takes. | | Fix words or style | a new round with `suno-v6` (or `suno-v6-cover` with the same seed) and the changed lyrics or style. Start from the lyrics you sent — never re-listen to your own take. Small fixes are a whole new take: say so in a line. | | Cover art | `generate_image` with `gpt-image-25-flare`, `quality: "medium"`, `width: 2048, height: 2048`: a square cover in the song's mood, the title as the only text; with their character → their look sheet as picture 1 (`character-sheet`). Check the title with `describe_media` "Read every word exactly." | | Music video | `musicvideo` with {track} and its lyrics. | Two variants they want to compare (two styles, two languages): two runs side by side, each with its own `generationAttemptId`. ## Pitfalls - Song runs take one to three minutes: check once after `retryAfterSeconds`, and do something free meanwhile (the cover art while the stems split). - **Suno says the audio "matches an existing recording"**: do not retry — the same track and its sibling take get the same answer. Never alter the audio to get past the check. Offer a new round (a beat only — `instrumental: true` — or a fresh take, then split that) or keeping the track as it is. - Stems of a mix not made by Suno also work (`audio_url` = the person's file), with lower quality. ## 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-song-from-a-hum/skills/music-after.md) - Updated from the owner's skill sources of 2026-10-11. Read: `music`, `musicvideo`, `character-sheet`. Source experiments and demo materials are historical; use the person's own approved media.