---
name: animate-audio-ref
description: Make the person's character say a given line, or move to a given soundtrack — H3 Max Reference to Video with the sheet as Image 1 and the line as Audio 1 (the lips follow it), or Seedance 2.5 with @Audio1; on Turbo a given audio only plays under the clip.
---
# A voice line or a soundtrack as Audio 1

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.

Read `animate` for the shared rules. {character sheet} as Image 1 + a voice line as Audio 1 → {character} saying the line. Also used as the whole soundtrack in `animate-film-scene-refs`. Audio 1 comes back as given, so it must already be {character}'s voice: the person's recording or their saved voice (`reels-voice`; re-voiced with `filmscene-sound` if needed). Never a demo voice.

## Choose

| Route | Model | Lips |
|---|---|---|
| Low cost | `minimax-h3-max-reference-to-video`, 480P (768P for the final) | follow Audio 1 |
| Quality | `seedance-2-5`: the sheet in `referenceGenerationIds` (@Image1), the line in `referenceAudioUrls` (@Audio1) | follow @Audio1; it speaks the line word for word, slightly faster — but it voices the line again itself: in a Russian test (2026-10-14) it slurred words, so check with `transcribe_media` |
| Turbo | `minimax-h3-max-turbo` with `targetAudioUrl` | do **not** follow: the audio only plays under the clip |

## Steps (H3 Max Reference to Video)

1. **The line**: 2–15 s — a `generationId`, `audioVoiceTaskId` or `audioFinishingTaskId` of the person's own audio (a span cut with `cut_audio_span`), read on the server. At most one own audio per request; it comes after any public audio URLs.
2. **Request**: `generate_video` with `referenceGenerationIds: [<sheet>]`, `referenceAudioUrls: [<the line>]`, `duration` = the line rounded up to whole seconds (at least the audio), `resolution: "480P"`, `aspectRatio: "16:9"` (or the format's). Quote first.
3. **Prompt** — say that Image 1 is only the look (blind), that Audio 1 is the character's voice and the whole soundtrack, and write the words out:
   ```
   Image 1 is only the look of {character}: exactly their face, hair and outfit from Image 1, nothing added. Image 1 never appears on screen.
   Audio 1 is {character}'s voice and the whole soundtrack: {character} says exactly the words of Audio 1, in its rhythm, lips in sync with every word: "<the words of the line>"
   Live-action film scene, one continuous shot: {framing and place}; {character} {action} and speaks the lines of Audio 1 {delivery}, {gaze}. Exactly one person is in the frame: {character}. The camera holds still.
   ```
   Keep service words (BEGINNING / THEN / END, headings) away from the quoted line: the model speaks prompt words that stand next to it.
4. **Check with the sound on**: `transcribe_media` the clip — the model may fill the time after the line with extra speech; cut such a tail with `trim_video`. `describe_media` with a `sourceRange` around a word: do the lips move with it?

## What to expect

- The voice is the reference itself — the model animates the face to it, it does not generate a new voice.
- Nothing is added on top: no music, no room — Audio 1 is the whole soundtrack (add room tone with `reels-room-sound`).

## Never

- Expect a new performance of the line (another voice, another rhythm).
- Leave the words out of the prompt.
- Describe the character's looks in the prompt — the look comes from Image 1 only.

## 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/acting/animate-ai-character/skills/animate-audio-ref.md)
- Updated from the owner's skill sources of 2026-10-11.

Read: `animate`, `reels-voice`, `filmscene-sound`, `reels-talking-head`. Source experiments and demo materials are historical; use the person's own approved media.