Sonilo V1 Text To Sfx

Sonilo V1 Text To Sfx

Playground

Sonilo Text to SFX generates sound effects from text prompts, with controllable duration and audio format for games, videos, ads, social content, and sound design workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Sonilo Text-to-SFX generates sound effects from a text prompt. Describe the sound source, environment, timing, motion, and intensity, then choose the target duration and output format.

Why Choose This?

• Text-to-sound-effect generation
  Generate sound effects directly from natural-language prompts.

• Precise sound direction
  Describe the sound source, action, environment, timing, and intensity for more controlled results.

• Flexible duration
  Generate sound effects in your prefer seconds.

• Multiple audio formats
  Export audio as wav, mp3, aac, or flac.

• Standard audio output
  Generated audio is returned as a URL in the standard WaveSpeed prediction response.

Parameters

How to Use

1. Write your prompt — Describe the sound source, action, environment, timing, and intensity.
2. Set duration — Choose a target duration from 1 to 180 seconds.
3. Choose audio format — Select wav, mp3, aac, or flac.
4. Submit — Generate the sound effect and retrieve the output URL.

Output

Returns one generated audio URL in the standard WaveSpeed prediction response.

The CDN file extension and MIME type match the selected audio_format.

Pricing

Best Use Cases

• Sound effect generation — Create custom SFX from text prompts.
• Video and game audio — Generate short sound assets for scenes, actions, impacts, ambience, and transitions.
• Content production — Create audio effects for ads, social videos, podcasts, and creative projects.
• Ambient sound design — Generate environmental sounds such as rain, wind, crowds, machinery, or room tone.
• Rapid audio prototyping — Quickly test different sound directions before final production.

Pro Tips

• Describe the sound source clearly, such as footsteps, glass breaking, thunder, engine noise, or crowd ambience.
• Include environment details, such as indoor room, forest, city street, underwater, or large hall.
• Mention timing and intensity, such as sudden, gradual, distant, close-up, soft, heavy, sharp, or explosive.
• Use shorter durations for quick effects and longer durations for ambience or background sound.
• Choose aac for general-purpose output, wav or flac for higher-quality workflows, and mp3 for broad compatibility.

## Authentication

For authentication details, please refer to the [Authentication Guide](/api-authentication).

## API Endpoints

### Submit Task & Query Result

<ApiTabs submitUrl={model.submitUrl} resultUrl={model.resultUrl} payload={model.defaultValues} />

## Parameters

### Task Submission Parameters

#### Request Parameters

<RequestParams params={model.params} />

#### Response Parameters

<SubmitResponse />

#### Result Request Parameters

| Parameter | Type | Required | Default | Description |
|-----------|------|----------|---------|-------------|
| id | string | Yes | - | Task ID |

#### Result Response Parameters

| Parameter | Type | Description |
|-----------|------|-------------|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., "success") |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction |
| data.model | string | Model ID used for the prediction |
| data.outputs | array&lt;string \| object&gt; | Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model. |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to poll for the prediction result |
| data.status | string | Status: `created`, `processing`, `completed`, or `failed` |
| data.created_at | string | ISO timestamp of when the request was created |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |