--- name: ad-ugc description: Make a UGC ad of up to 15 s — the person's character confesses, opens and tries the product and ends on a call to action — with the voice as Audio 1 on H3 Max Reference to Video (the lips follow it), or the lines in a Turbo prompt and the voice changed after; Seedance 2.5 as the quality route. --- # The creator and the product 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 `ad` for the shared rules. > **Entry level:** the lines go into an H3 Max Turbo prompt and the creator's voice is changed in the finished clip (`reels-lipsync-turbo`). The voice + H3 Max Reference to Video method below is the precise variant: there the lips follow the voice. On Turbo a given audio only plays under the clip. **Quality route:** Seedance 2.5 (`seedance-2-5`) with the same inputs as @Image1… / @Audio1 does this job much better; quote both. ## Steps 1. **Script of up to 15 s**: the hook (a confession, a whisper) → the product in action (open, sip) → the benefit in the creator's words → the call to action ("link in bio") with a wink. 2. **Voice**: `generate_voice_audio` with the creator's saved voice, `model: "eleven_v4"`, tags for delivery: `"[whispers] Okay, I need to confess something... [normal] … [excited] … [playful] …"` (`reels-emotion-tags`). `transcribe_media` → the word times. 3. **Start frame**: `generate_image` with `gpt-image-25-flare`, `quality: "low"`, `width: 1152, height: 2048`; picture 1 = the character sheet (face, hair, clothes), picture 2 = the product sheet; "as if they film themselves at arm's length, the camera itself never seen", the product on the counter with the label to camera. 4. **Video**: `generate_video` with `minimax-h3-max-reference-to-video`, `aspectRatio: "9:16"`, `resolution: "480P"`, `duration` = the voice rounded up; `referenceGenerationIds`: [character sheet, product sheet, start frame], `referenceAudioUrls`: [the voice's `audioVoiceTaskId`]. JSON prompt: `output` (a vertical UGC video, hand-held, two jump cuts), `references` (Image 1 only the face, hair and clothes; Image 2 "exactly this product … every time"; Image 3 the first frame), shots `from`/`to` on the word times with the line in quotes; rules: one product, the camera never seen, no phones, no subtitles. 5. **Sound**: the generation's voice, a short room reverb (`add_audio_reverb`, `preset: "room"`) and room tone about 13 dB under it (`reels-room-sound`). A product sound (the can cracking): ElevenLabs Sound Effects (`generate_audio` with `model: "elevenlabs-sound-effects-v2"`, 1–2 s) placed at its moment with `offsetSeconds` in `mix_audio_tracks`, under the voice — or a real recording, or the Seedance route. ## Check `transcribe_media` the clip against the script; `extract_video_frame` where the label faces the camera and `describe_media` "Read the label exactly; is it the same product as the sheet?". ## 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-video-ad/skills/ad-ugc.md) - Updated from the owner's skill sources of 2026-10-11. Read: `ad`, `ad-product-sheet`, `reels-talking-head`, `reels-voice`, `reels-room-sound`. Source experiments and demo materials are historical; use the person's own approved media.