# PixVerse Sound Effect

PixVerse Sound Effect adds AI-generated sound effects or background music to an existing video. Optionally describe the sound you want or let the model auto-generate based on the video content. Optionally keep the original audio.

## API Information

- **Model Slug:** pixverse-sound-effect
- **Branded URL:** https://www.eachlabs.ai/pixverse/pixverse-features/pixverse-sound-effect
- **Provider:** PixVerse
- **Category:** Video to Video
- **Output Type:** video
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** Flat per-second pricing — same rate for all qualities: $0.01 per second of input video.Examples: 10s = $0.10, 30s = $0.30.
- **Estimated Processing Time:** 30 seconds
- **Last Updated:** 2026-04-27
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/pixverse-sound-effect

## Pricing

- **Charge Type:** dynamic
- **Pricing Details:** Flat per-second pricing — same rate for all qualities: $0.01 per second of input video.Examples: 10s = $0.10, 30s = $0.30.

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| Rule 1 | Flat per-second pricing — same rate for all qualities: $0.01 per second of input video.Examples: 10s = $0.10, 30s = $0.30. |

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| video_url | string | Yes | - | mp4, mov, webm, avi | URL of the video to add sound to. The video will be uploaded to PixVerse for processing. |
| sound_effect_content | string | No | - | - | Describe the sound you want (e.g. 'rainforest ambience with bird calls'). If not provided, the model auto-generates based on video content. |
| original_sound_switch | boolean | No | false | - | Keep the original audio from the video alongside the generated sound. Default: false (replace). |

## Example Request

```bash
curl -X POST https://api.eachlabs.ai/v1/prediction/ \
  -H "X-API-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "pixverse-sound-effect",
  "input": {
    "video_url": "https://cdn-us.eachlabs.ai/uploads/b189c44f-3a3c-4259-8c72-baa673b8e72e.mp4"
  }
}'
```

## Output Schema

Response returned by `GET /v1/prediction/{id}` when the job completes:

```json
{
  "status": "success",
  "predictionID": "string",
  "output": "string (URL of generated video)",
  "metrics": {
    "predict_time": "number (seconds)"
  }
}
```

## Polling

```bash
curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \
  -H "X-API-Key: YOUR_API_KEY"
```

| Status | Meaning |
|--------|---------|
| `processing` | Still running — poll again |
| `success` | Done — read `output` |
| `error` | Failed — read `message` / `details` |

## Webhook (alternative to polling)

Pass `"webhook_url": "https://your.host/path"` in the create request. Eachlabs POSTs this payload when the job ends:

```json
{
  "exec_id": "prediction-uuid",
  "status": "succeeded",
  "output": "https://...",
  "error": ""
}
```

`status` is `"succeeded"` or `"failed"`. `exec_id` equals the `predictionID` from create. Return 2xx within 30 seconds.

## Errors

Error body: `{ "status": "error", "message": "...", "details": "..." }`

| Code | Meaning |
|------|---------|
| `400` | Invalid input |
| `401` | Missing / invalid `X-API-Key` |
| `404` | Unknown model or prediction id |
| `429` | Rate limit — 100 creates / min, 10 concurrent per key |
| `5xx` | Retry with backoff |

## Overview

**PixVerse | Sound Effect | Video Audio Generation Overview**

PixVerse | Sound Effect | Video Audio Generation enhances existing videos by adding AI-generated sound effects or background music, solving the challenge of syncing audio to visuals without manual editing. Provided by PixVerse, this tool integrates seamlessly into their advanced video generation ecosystem, including models like V6 and C1 that support native audio output. Its primary differentiator is the option to auto-generate sounds based on video content analysis or use custom descriptions, while optionally preserving original audio for flexible post-production workflows on **each::labs**.

Users upload a video, describe desired audio like "thunderstorm with dramatic music," or enable auto-mode for context-aware effects. This makes it ideal for quick enhancements in content creation, distinguishing it from general video-to-video models by focusing on audio-video synchronization. Available via the PixVerse | Sound Effect | Video Audio Generation API, it supports creative and commercial projects with high fidelity.

## Usage Notes

- API Base URL: `https://api.eachlabs.ai/v1`
- Authentication: send `X-API-Key: YOUR_API_KEY`. Generate a key from the Eachlabs dashboard at https://www.eachlabs.ai/dashboard/api-keys.
- File-typed parameters (`*_url`, `image_url`, `video_url`, `audio_url`, etc.) accept publicly-reachable HTTPS URLs only. Upload your asset first (GCS / S3 / your CDN) and pass the resulting URL. Data-URIs and localhost URLs are rejected.
- For structured parameters (arrays / objects) send real JSON values, not stringified payloads.
- Monetary values are reported in USD; per-token / per-megapixel rates may be billed in micro-cents internally.
- Prefer `webhook_url` over polling for long-running predictions — see the Webhook Callback section.