# Sonilo v1.1 Video to Sound Effects - Core.Today AI API

> Sonilo v1.1 video-to-sound-effects via Fal.AI. Adds AI-generated sound (ambience, effects, foley) to an input video — auto-captions the scene if no prompt is given, or accepts per-segment sound descriptions for finer control.

- **Provider**: Sonilo
- **Model ID**: sonilo/v1.1/video-to-sound-effects
- **Category**: Audio & TTS
- **Credits**: 310 per video (flat rate, regardless of length)
- **Speed**: Fast
- **Quality**: Standard

## Features
- Adds ambience, sound effects, and foley to silent or under-scored video
- Auto-captions the scene when no prompt is given
- Per-segment sound descriptions for finer, time-ranged control
- Output audio matches the input video's length automatically
- Choice of AAC, MP3, WAV, or FLAC for the returned audio file
- Billed as a flat rate per video, regardless of the video's length

## Use Cases
- Adding foley and ambience to silent stock or AI-generated video footage
- Sound-designing short films or social clips without a dedicated sound team
- Automatically captioning and scoring raw footage before final edit
- Fine-tuning sound per scene using segment-level descriptions

## API Endpoint

Base URL: https://api.core.today/v1
Create Prediction: POST /predictions
Get Status: GET /predictions/{job_id}

## Authentication
Header: X-API-Key: YOUR_API_KEY

## Input Parameters

### Required
- **video_url**: string - The video to add sound to (public URL, or upload a file). The generated audio matches the video's length.

### Optional
- **prompt**: string - Optional. Describe the kind of sound you want; it steers the generated audio for every scene. Leave empty to caption the video automatically.
- **segments**: array - Optional. Split the video into time ranges, each with its own sound description. Leave empty to split into scenes automatically.
- **audio_format**: string (default: aac) - Format of the returned audio file: aac (default), mp3, wav, or flac. (The video with sound is always AAC.)
  Options: wav, mp3, aac, flac

## Examples

### Auto-captioned foley for silent footage
Add automatically generated ambience and sound effects to a silent video without specifying a prompt.
```json
{
  "model": "sonilo/v1.1/video-to-sound-effects",
  "input": {
    "video_url": "https://storage.googleapis.com/falserverless/model_tests/video_models/mmaudio_input.mp4",
    "audio_format": "aac"
  }
}
```

### Prompt-guided sound design
Steer the sound design with an explicit prompt and request the standalone audio track as WAV.
```json
{
  "model": "sonilo/v1.1/video-to-sound-effects",
  "input": {
    "video_url": "https://example.com/city-street-timelapse.mp4",
    "prompt": "Busy city street ambience with distant traffic, footsteps, and occasional car horns.",
    "audio_format": "wav"
  }
}
```

## Response Format
```json
{
  "job_id": "abc123",
  "status": "pending | processing | completed | failed",
  "result": "URL or data (when completed)"
}
```

## Usage Flow
1. POST /predictions with model and input -> receive job_id
2. GET /predictions/{job_id} -> poll until status is completed or failed
3. Result contains output URL(s)

## Tips
- Leave prompt empty to let the model auto-caption the scene — useful for a quick first pass on unfamiliar footage.
- Use segments when different parts of the video need distinctly different sound treatment instead of one uniform description.
- It's billed as a flat rate per video regardless of the video's length, so longer footage doesn't cost more per call.
- Pick wav or flac when you need the standalone audio track for further mixing; aac is fine for direct playback.

## Documentation
https://fal.ai/models/sonilo/v1.1/video-to-sound-effects