# Sonilo v1.1 Text to Music - Core.Today AI API

> Sonilo v1.1 text-to-music via Fal.AI. Generates up to 3 distinct music tracks (up to 600 seconds each) from a text description of the desired sound.

- **Provider**: Sonilo
- **Model ID**: sonilo/v1.1/text-to-music
- **Category**: Audio & TTS
- **Credits**: 520 per second per generated track
- **Speed**: Fast
- **Quality**: Standard

## Features
- Generates full music tracks from a text description
- Up to 600 seconds (10 minutes) per track
- Generate up to 3 distinct track variations in a single call
- Billing scales with requested duration and number of samples

## Use Cases
- Background music beds for videos, presentations, or podcasts
- Jingles or short branded music stings
- Generating multiple stylistic variations of a track to pick the best fit
- Royalty-free-style music for content prototypes before final production

## 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
- **prompt**: string - Text prompt describing the music to generate.

### Optional
- **duration**: integer (default: 90) - Requested output duration in seconds (max 600). Also used for billing (one billable unit per second per sample, rounded up).
- **num_samples**: integer (default: 1) - How many distinct music tracks to generate.

## Examples

### Neo-soul background track
Generate a single 90-second track blending several soul-adjacent genres for use as background music.
```json
{
  "model": "sonilo/v1.1/text-to-music",
  "input": {
    "prompt": "A blend of R&B warmth, soul depth, neo-soul texture, gospel spirit, pop clarity, and jazz sophistication.",
    "duration": 90,
    "num_samples": 1
  }
}
```

### Multiple variations for a short jingle
Generate 3 short variations of an upbeat jingle in one call to compare and choose the best fit.
```json
{
  "model": "sonilo/v1.1/text-to-music",
  "input": {
    "prompt": "An upbeat, playful jingle with light percussion and a catchy melodic hook.",
    "duration": 15,
    "num_samples": 3
  }
}
```

## 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-only for a single track, or raise num_samples up to 3 to get variations in one call.
- Billing scales with both duration and num_samples, so set duration to only what you actually need before generating multiple samples.
- Describe genre, mood, and instrumentation together in the prompt (e.g. genre blends, tempo, energy) for more distinctive results.
- For long-form background music, request the full duration up front rather than stitching several short generations together.

## Documentation
https://fal.ai/models/sonilo/v1.1/text-to-music