--- name: music-write description: Write song lyrics and the Suno style line for the person — structure tags, the hook from their own words, the language of the seed, length by duration, the style formula (genre + voice + instruments + tempo + mood, no artist names) and negative tags; also a song from an idea or from their own lyrics. --- # Lyrics and the style line 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. ## Lyrics - **Structure tags on their own lines**: `[Intro]`, `[Verse 1]`, `[Pre-Chorus]`, `[Chorus]` (or `[Hook]` for rap), `[Verse 2]`, `[Bridge]`, `[Outro]`. Suno sings what is between them; nothing in tags is sung. - **Length by `duration`**: about 150 s → an intro, two verses of 8 lines, the chorus three times, a 4-line bridge, an outro. 30–60 s → one verse and one chorus. - **Repeats**: a bare `[Chorus]` tag is sung as the chorus again. Write it out in full only when a repeat must change. - **Their words first**: a line from their seed or their message is the hook or chorus, word for word (only their own corrections). - **Language** — the language of the seed or of their lyrics; lines that rhyme and scan in that language, not a translation. - **Concrete pictures** from the theme (places, objects, one small story), short lines that can be sung in one breath; the chorus repeats identically every time. - **Ad-libs** of the seed (yeah, hey, oh…) stay as written — they carry the flow. - **Their own lyrics** — keep them exactly; only add tags where the sections are obvious. Never "improve" their words unasked. - Never write the words of an existing song from memory; never name real people in a way that mocks or targets them. ## Style line (`style`, at most 1000 characters; one line, comma-separated) `, , <2–4 instruments or sounds>, BPM, , ` - Start from MusicBrainz: the picked vibe's style line (`describe_music_vibes`) or a named artist's (`describe_music_style`); then add the tempo, delivery and mood heard in the seed (`music-hum`), the voice and 2–4 instruments. - **No artist or band names** — describe the sound. - Example shape (write a fresh one each time): "indie pop, warm female vocal in English, clean electric guitar, soft analog synth, 100 BPM, late-night city mood, catchy chorus". - `negative_tags` — what must not come: "female vocal" for a male rap, "english lyrics" for a Russian song, a genre it drifts to. ## A song from an idea (no seed) Ask nothing you can decide: one vibe question from MusicBrainz (three genres that fit the idea → `describe_music_vibes` → "like …" options and a free answer); the voice goes into the style unless they care. Their pick comes → write the lyrics and run `suno-v6` in that same turn, with `title` (at most 80 characters). For a beat or a backing track: `instrumental: true`, no `lyrics`, `duration` = the length they need. "Make it now" / "you decide" / "skip": no question — choose the idea, the genre and the title yourself, say them in one line and run the song. Keep the title, the exact lyrics and the style as a note on the board (`execute_board_action` with `addTextNote`) when a board is open. ## 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-write.md) - Updated from the owner's skill sources of 2026-10-11. Read: `music`, `music-refs`, `music-after`. Source experiments and demo materials are historical; use the person's own approved media.