API reference · Mirelo

mirelo/sfx1.6/text-to-audio

Integrate this model through SandBase's unified API, with production-ready schemas and examples.

AUDIOAsyncOpen model

Production endpoint

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

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

Model IDmirelo/sfx1.6/text-to-audio

Input Schema

7 parameters · 0 required · 7 optional

Parameter	Type	Required	Description
`seed`	integer	Optional	Seed for generation. -1 or None for random. · Min: -1
`ambience`	boolean	Optional	When true, generate a seamlessly loopable ambience tile (room tone, rain, drones, etc.). When false, generate a generic text-conditioned SFX of `duration` seconds. · Default: false
`duration`	integer	Optional	Duration of the generated audio in seconds. · Min: 0.1 · Max: 60 · Default: 10
`num_samples`	integer	Optional	Number of variations to generate. · Min: 1 · Max: 4 · Default: 1
`text_prompt`	string	Optional	Text prompt for the generated audio. · Min length: 4
`double_output`	boolean	Optional	Only used when ambience=true: concatenate the loop with itself for a 2x-length output. · Default: false
`upload_audio_format`	string	Optional	Audio format for the returned files. · Options: wav, mp3, aac, flac · Default: "wav" 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": "mirelo/sfx1.6/text-to-audio",
  "ambience": false,
  "duration": 10,
  "num_samples": 1,
  "text_prompt": "city ambience",
  "double_output": false,
  "upload_audio_format": "wav",
  "prompt": "a beautiful sunset over mountains"
}'

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

← Back to Mirelo SFX1.6