Video
sound-to-video
The picture follows the sound you drop.
<!-- Generated by apps/docs/scripts/gen-tools.mjs. Do not edit here: the words live in apps/web/src/lib/tools/sound-to-video.tool.json (agent, hint) and packages/shared/src/tools/setting-hints.ts. --> On the rail as **sound-to-video**. ## When to use it Turning a piece of audio into a clip cut exactly to its length, when the sound should set the pace and the picture needs to follow it. ## When to reach for something else The audio alone does not say what appears on screen: it needs either a written description or a start frame to know what to show. Sound is capped between 2 and 20 seconds, and the clip always runs exactly that long. ## How to use it 1. Drop a sound onto the card's **Sound** slot. 2. Write what you want in **Prompt**. 3. Pick a model in the pill at the top of the card, or keep **LTX 2.5 Fast**. 4. Press **Run**. ## On the card | Control | What it does | Choices | | - | - | - | | Sound | The sound the clip is cut to. Drop one from the board or your computer. | One sound | | Prompt | What is on screen. Optional once a start frame is set, but the run needs one of the two. | Your words | | Run | Starts the run. The number on it is what this run costs in credits, worked out before you press. | | | ×1 | Runs the card several times in a row with the same settings. | 1 to 99 | ## Models The pill at the top of the card picks the model. **LTX 2.5 Fast** is the one a new card starts on. | Model | Good for | | - | - | | [LTX 2.5 Fast](#ltx-25-fast) | Picture cut to a piece of sound, 2 to 20 seconds, at 1080p and exactly as long as the audio, from a start frame or a prompt; the default tier of the two. | | [LTX 2.5 Pro](#ltx-25-pro) | The quality tier for sound-driven clips: the same 2 to 20 second, 1080p, audio-length render with more compute spent on holding the picture together, for the take that has to hold up. | ### LTX 2.5 Fast **Not the one for:** It needs a start frame or a prompt on top of the audio, since the sound decides length and pacing but not content; there is no duration, resolution or camera-move setting, and shapes are 16:9, 9:16 or auto. Behind the settings button: | Setting | What it does | Choices | | - | - | - | | Start Frame (optional) | Sets the look the clip opens on. Supply this or a prompt. | One picture | | Aspect Ratio | The shape of the result, like 1:1 square, 16:9 wide, or 9:16 tall. "Match input" copies the source shape. | Auto, Horizontal 16:9, Vertical 9:16 | ### LTX 2.5 Pro **Not the one for:** Costs more per second of audio than the fast tier for the same shape and limits; it still needs a start frame or a prompt, and the clip length is always the audio length. Behind the settings button: | Setting | What it does | Choices | | - | - | - | | Start Frame (optional) | Sets the look the clip opens on. Supply this or a prompt. | One picture | | Aspect Ratio | The shape of the result, like 1:1 square, 16:9 wide, or 9:16 tall. "Match input" copies the source shape. | Auto, Horizontal 16:9, Vertical 9:16 |On the rail as sound-to-video.
When to use it
Section titled “When to use it”Turning a piece of audio into a clip cut exactly to its length, when the sound should set the pace and the picture needs to follow it.
When to reach for something else
Section titled “When to reach for something else”The audio alone does not say what appears on screen: it needs either a written description or a start frame to know what to show. Sound is capped between 2 and 20 seconds, and the clip always runs exactly that long.
How to use it
Section titled “How to use it”- Drop a sound onto the card’s Sound slot.
- Write what you want in Prompt.
- Pick a model in the pill at the top of the card, or keep LTX 2.5 Fast.
- Press Run.
On the card
Section titled “On the card”| Control | What it does | Choices |
|---|---|---|
| Sound | The sound the clip is cut to. Drop one from the board or your computer. | One sound |
| Prompt | What is on screen. Optional once a start frame is set, but the run needs one of the two. | Your words |
| Run | Starts the run. The number on it is what this run costs in credits, worked out before you press. | |
| ×1 | Runs the card several times in a row with the same settings. | 1 to 99 |
Models
Section titled “Models”The pill at the top of the card picks the model. LTX 2.5 Fast is the one a new card starts on.
| Model | Good for |
|---|---|
| LTX 2.5 Fast | Picture cut to a piece of sound, 2 to 20 seconds, at 1080p and exactly as long as the audio, from a start frame or a prompt; the default tier of the two. |
| LTX 2.5 Pro | The quality tier for sound-driven clips: the same 2 to 20 second, 1080p, audio-length render with more compute spent on holding the picture together, for the take that has to hold up. |
LTX 2.5 Fast
Section titled “LTX 2.5 Fast”Not the one for: It needs a start frame or a prompt on top of the audio, since the sound decides length and pacing but not content; there is no duration, resolution or camera-move setting, and shapes are 16:9, 9:16 or auto.
Behind the settings button:
| Setting | What it does | Choices |
|---|---|---|
| Start Frame (optional) | Sets the look the clip opens on. Supply this or a prompt. | One picture |
| Aspect Ratio | The shape of the result, like 1:1 square, 16:9 wide, or 9:16 tall. “Match input” copies the source shape. | Auto, Horizontal 16:9, Vertical 9:16 |
LTX 2.5 Pro
Section titled “LTX 2.5 Pro”Not the one for: Costs more per second of audio than the fast tier for the same shape and limits; it still needs a start frame or a prompt, and the clip length is always the audio length.
Behind the settings button:
| Setting | What it does | Choices |
|---|---|---|
| Start Frame (optional) | Sets the look the clip opens on. Supply this or a prompt. | One picture |
| Aspect Ratio | The shape of the result, like 1:1 square, 16:9 wide, or 9:16 tall. “Match input” copies the source shape. | Auto, Horizontal 16:9, Vertical 9:16 |