---
name: animate-audio-ref
description: "Give your AI character a voice or a soundtrack with MiniMax H3 Max reference-to-video — an audio reference is played back as given (correlation 0.96 for a voice line, 0.89 for a drum solo) and the picture is animated to it; write the words in the prompt too. Use when the user says lip-sync, make my character say, voice, talking head, dialogue line, audio reference, soundtrack, липсинк, озвучка. Part of the animate meta-skill."
---

These creative references describe source experiments with external tools. Use your own supported account and tools; this download installs no automation. Settings and timings are experimental observations, not current FlashBoards availability.

# animate-audio-ref · a voice line or a soundtrack as Audio 1

> 🏆 **Source quality recommendation:** Seedance 2.5 reference-to-video (`bytedance/seedance-2.5/reference-to-video`, references as @Image1… / @Audio1…, 4–30 s, native sound) is the supplier's preferred quality route. That recommendation is supported by the product-commercial comparison, not a measurement of every character task. The H3 methods below retain their own measured inputs, settings and timings. Use supported external tools; this is not a FlashBoards integration claim.

{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` (a film's music).
Audio 1 comes back as given, so it must already be {character}'s voice: the person's recording or the voice on their character card (re-voiced with `filmscene-sound` if needed). Never a demo voice.

## Choose

| Priority | Settings | Time | Result |
| --- | --- | --- | --- |
|  tested | `minimax/h3-max/reference-to-video` · **7 s** (whole seconds, ≥ the audio) · **480P** · 16:9 · sheet + 6.7 s voice | not measured | the voice is Audio 1 itself; mouth opens and closes with the phrases |
| 🏆 768P | same at 768P | not tested for voice | — |
| ⚡ on Turbo | image-to-video with `target_audio_url` pins a track as the soundtrack (used in `animate-storyboard-turbo`) | not measured | lip-sync on Turbo not tested |



## Steps

1. Cut the line (2–15 s per clip, 15 s of audio together). Attach the clip through your supported external tool.
2. Body:
   ```json
   {"duration": 7, "resolution": "480P", "aspect_ratio": "16:9", "prompt_expansion_mode": "disabled",
    "reference_image_urls": ["<{character sheet}>"], "reference_audio_urls": ["<line.mp3>"]}
   ```
3. Prompt — say that Image 1 is only the look (blind, no looks in words), 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.
   ```
4. Generate through your supported external tool; watch with the sound on.

## What to expect

- The voice is the reference itself (correlation **0.96** at zero offset) — the model animates the face to it, it does not generate a new voice.
- Nothing is added on top: no music, no engine — Audio 1 is the whole soundtrack.
- **Lip-sync accuracy: not measured** — judge it by eye with the sound on.

## Never

- Expect a new performance of the line (another voice, another rhythm) — Audio 1 comes back as given.
- Leave the words out of the prompt — we always wrote them; without them it was not tested.
- Describe the character's looks in the prompt — the look comes from Image 1 only.

## Example run (reference only — never reuse its files, prompts, faces, voices or frames for a person)

6.7 s of narration from *Gone Girl* (2014) + the demo character Mara Vale's sheet → Mara saying the lines at the wheel of an old car: a medium close-up through the windshield at golden hour, both hands on the wheel, flat and calm, eyes on the road, a faint bitter smile at the end. The historical prompt still spelled out Mara's looks in words; the blind wording above replaces that.