Sonilo modelsaudio generation api

sonilo/1.1/text-to-sound-effects

Name: V1.1 Text to Sound Effects
Author: Sonilo

1.1 Text To Sound Effects is Sonilo's AI audio generation model. Produce high-quality music tracks, sound effects, and audio landscapes from natural language prompts.

Input

Prompt(string)

Describe the sound you want to create.

Duration(integer)

1180

How long the audio should be, in seconds. Range: 1 to 180.

Audio Format(string)

Audio file format: aac (default), mp3, wav, or flac. Allowed values: wav, mp3, aac, flac.

Num Samples(integer)

Number of output samples to generate and bill. Minimum: 1.

Idle

Example output — click Run to generate your own

Production endpoint

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

POSThttps://api.sandbase.ai/v1/run

Model IDsonilo/1.1/text-to-sound-effects

Input Schema

4 parameters · 1 required · 3 optional

Parameter	Type	Required	Description
`prompt`	string	Required	Describe the sound you want to create.
`duration`	integer	Optional	How long the audio should be, in seconds. · Min: 1 · Max: 180 · Default: 8
`num_samples`	integer	Optional	Number of output samples to generate and bill. · Min: 1 · Default: 1
`audio_format`	string	Optional	Audio file format: aac (default), mp3, wav, or flac. · Options: wav, mp3, aac, flac · Default: "aac" wavmp3aacflac

Output Schema

Field	Type	Description
`id`	string	Unique identifier for the generation task
`status`	string	Task status: pending, running, completed, failed, timeout
`model`	string	Model used for the generation
`outputs`	array	Array of output items
`outputs[].url`	string	URL of the generated artifact
`outputs[].content_type`	string	MIME type (e.g. image/png, video/mp4)
`error`	object \| null	Error details if failed, null on success
`error.type`	string	Machine-readable error type code
`error.message`	string	Human-readable error description

Async Workflow

This model uses asynchronous execution. Submit a request and poll for the result.

Submit — POST to /v1/run, receive an id
Poll — GET /v1/run/{id} until status is completed, failed, or timeout
Retrieve — Read outputs from the completed response

Code Examples

Ready-to-run snippets

# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
  "model": "sonilo/1.1/text-to-sound-effects",
  "prompt": "Heavy rain on a tin roof with distant rolling thunder",
  "duration": 8,
  "num_samples": 1,
  "audio_format": "aac"
}'

# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
  -H "Authorization: Bearer YOUR_API_KEY"

← Back to V1.1 Text to Sound Effects

API README

PRICED DRAFT — MANUAL REVIEW REQUIRED exact_model_mode: sonilo/v1.1/text-to-sound-effects original_unit: Your request will cost $0.0018 per second of output and per sample. method: per-output-second per-sample price; restored sample count result_base_price: 0.0144 result_price_formula: (params.duration ?? 8) * (params.num_samples ?? 1) * 0.0018 review_status: pending; model remains disabled checked_at: 2026-08-16