# SAM Audio · Video-Prompted Sound Separation

Edit and transform audio with SAM Audio · Video-Prompted Sound Separation from fal through one Spiral API key. Isolates the sound made by a chosen object in a video, picked out with a mask video or a text description, and returns it. It runs in the background and returns audio. Pay as you go, with no subscription.

- Provider: fal
- Category: Audio
- Runs: In the background
- Returns: audio
- Released: 2025-12-30
- Tool id: `fal` / `fal-ai/sam-audio/visual-separate`
- Page: https://spiral.ai/tools/fal/fal-ai/sam-audio/visual-separate

## Pricing

$0.13 per 30 seconds of audio for its two tracks, at least 30 seconds. Each extra reranking candidate: $0.065 per 30 seconds.

## Limits

- Longest queue wait: 1 hour
- Run deadline: 30 minutes
- Longest run, end to end: 255 minutes
- Largest inline input: 1 MB
- Largest input file: 2 GB
- Largest output: 5 GB

## Input

| Field | Kind | Allowed | Default | Description |
| --- | --- | --- | --- | --- |
| `video_url` (required) | URL or file |  | — | URL of the video file to process (MP4, MOV, etc.) |
| `mask_video_url` | URL or file |  | — | URL of the mask video (binary mask indicating target object). Black=target, White=background. |
| `prompt` | text |  |  | Text prompt to assist with separation. Use natural language to describe the target sound. |
| `reranking_candidates` | number (whole) | 1 to 4 | 1 | Number of candidates to generate and rank. Higher improves quality but increases latency and cost. |
| `acceleration` | one of | fast, balanced, quality | balanced | The acceleration level to use. |
| `max_chunk_duration` | number | 10 to 60 | 60 | Maximum audio duration (in seconds) to process in a single pass. Longer audio will be chunked with overlap and blended. |
| `chunk_overlap` | number | 0 to 30 | 5 | Overlap duration (in seconds) between chunks for crossfade blending. |
| `output_format` | one of | wav, mp3 | wav | Output audio format. |

## Example

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "fal",
    "model": "fal-ai/sam-audio/visual-separate",
    "input": {
      "video_url": "https://v3b.fal.media/files/b/0a8850d1/gff7zKI-6XwIbBBip4946_office.mp4"
    }
  }'
```

Try it in the Playground: https://spiral.ai/start?provider=fal&model=fal-ai%2Fsam-audio%2Fvisual-separate

## Common questions

### SAM Audio · Video-Prompted Sound Separation

**How much does SAM Audio · Video-Prompted Sound Separation cost?**

$0.13 per 30 seconds of audio for its two tracks, at least 30 seconds. Each extra reranking candidate: $0.065 per 30 seconds. You pay as you go from one Spiral balance, with no subscription, and a failed run is not charged.

**How do I use SAM Audio · Video-Prompted Sound Separation through an API?**

Send `POST /v1/runs` with `"provider": "fal"`, `"model": "fal-ai/sam-audio/visual-separate"` and the input fields on this page, using one Spiral API key. It runs in the background: poll the run, or name a webhook to be told when it finishes.

**Do I need an account with fal to use SAM Audio · Video-Prompted Sound Separation?**

No. Spiral runs it on its own fal account and charges your Spiral balance.

**Can my AI agent use SAM Audio · Video-Prompted Sound Separation?**

Yes. Agents find and run it through Spiral's MCP server, CLI or agent skill, with the same API key.

