Mirelo modelsimage generation api

mirelo/sfx1.6/extend-audio

Name: Mirelo SFX1.6
Author: Mirelo

Sfx1.6 Extend Audio by Mirelo - advanced AI model for audio-to-audio. Delivers high-quality results with fast inference, suitable for both creative and production workflows.

Input

Audio Url(string)

URL of the audio prefix to extend. The prefix duration must be 3–59 seconds; the total output (prefix + append_duration) is capped at 60 seconds.

Seed(integer)

Seed for generation. -1 or None for random. Minimum: -1.

Append Duration(number)

157

How many seconds to add after the prefix. Total output = prefix duration + append_duration, capped at 60s. Minimum 1s, maximum 57s (60s cap minus the 3s prefix minimum). Range: 1 to 57.

Upload Audio Format(string)

Audio format for the returned files. Allowed values: wav, mp3, aac, flac.

Ambience(boolean)

When true, run the extend+loop path: extend the prefix and stitch the end back to the prefix start so the tile loops seamlessly. When false, run a one-shot extension.

Double Output(boolean)

Only used when ambience=true: concatenate the loop with itself for a 2x-length output.

Num Samples(integer)

Number of variations to generate. Range: 1 to 4.

Text Prompt(string)

Optional text prompt guiding the extension.

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 IDmirelo/sfx1.6/extend-audio

Input Schema

8 parameters · 0 required · 8 optional

Parameter	Type	Required	Description
`seed`	integer	Optional	Seed for generation. -1 or None for random. · Min: -1
`audio`	string	Optional	URL of the audio prefix to extend. The prefix duration must be 3–59 seconds; the total output (prefix + append_duration) is capped at 60 seconds.
`ambience`	boolean	Optional	When true, run the extend+loop path: extend the prefix and stitch the end back to the prefix start so the tile loops seamlessly. When false, run a one-shot extension. · Default: false
`num_samples`	integer	Optional	Number of variations to generate. · Min: 1 · Max: 4 · Default: 1
`text_prompt`	string	Optional	Optional text prompt guiding the extension.
`double_output`	boolean	Optional	Only used when ambience=true: concatenate the loop with itself for a 2x-length output. · Default: false
`append_duration`	number	Optional	How many seconds to add after the prefix. Total output = prefix duration + append_duration, capped at 60s. Minimum 1s, maximum 57s (60s cap minus the 3s prefix minimum). · Min: 1 · Max: 57 · Default: 10
`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/extend-audio",
  "audio": "https://static.sandbase.ai/examples/mirelo/sfx1.6/extend-audio/input_audio_0.aac",
  "ambience": false,
  "num_samples": 1,
  "text_prompt": "birds chirping",
  "double_output": false,
  "append_duration": 10,
  "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

API README

Sfx1.6 Extend Audio

Sfx1.6 Extend Audio is built for context-aware sound design, with this exact route focused on seamless audio continuation. Sfx1.6 Extend Audio by Mirelo - advanced AI model for audio-to-audio. Delivers high-quality results with fast inference, suitable for both creative and production workflows. It is designed for production workflows that need a clearly scoped media operation instead of a generic assistant response, preserving the supplied direction while returning an artifact ready for review, iteration, or downstream assembly.

The request surface keeps creative direction and delivery choices explicit through seed, ambience, audio_url, sync_mode, num_samples, text_prompt. Teams can lock source material, describe the intended result, choose supported output controls, and rerun the same request structure across variations. This makes experiments easier to compare and larger pipelines easier to operate without hiding important decisions inside an opaque preset.

Highlights

Seamless Audio Continuation. The mirelo/sfx1.6/extend-audio route is dedicated to seamless audio continuation, keeping inputs and outputs matched to this operation.
Timing-Sensitive Effects. Within mirelo/sfx1.6/extend-audio, documented prompt and media controls direct timing-sensitive effects while keeping the brief close to the result.
Production-Ready Audio Output. The mirelo/sfx1.6/extend-audio result provides production-ready audio output in a machine-consumable form for review and downstream production.
Route-specific control. For mirelo/sfx1.6/extend-audio, documented controls include seed, ambience, audio_url, sync_mode, num_samples, text_prompt, defining the supported variation space for this exact route.

Pricing

Billing status	Price
Current quote	Check the console before submitting.

When to Use

Scenario	Why it fits
Choose this route	When the deliverable is specifically seamless audio continuation, not a neighboring generation or editing task.
Production iteration	When creative teams need repeatable timing-sensitive effects with an explicit request payload.
Automated pipelines	When production-ready audio output must flow into review, storage, compositing, or publishing.
Controlled variations	When a stable brief should be rerun while changing only documented inputs.
Prototype to scale	When the same `mirelo/sfx1.6/extend-audio` contract should serve a single experiment and a larger batch later.

Prompt Guide

Lead with the subject or source, then state the transformation, important spatial or temporal details, style, and finish. Supply only documented fields, keep media URLs reachable, and vary one control at a time when comparing outputs.

{
  "seed": 1,
  "ambience": false
}

Technical Specs

Property	Value
Model ID	`mirelo/sfx1.6/extend-audio`
Required inputs	None documented
`seed`	integer
`ambience`	boolean; default: false
`audio_url`	string
`sync_mode`	boolean; default: false
`num_samples`	integer; default: 1
`text_prompt`	string
`double_output`	boolean; default: false
`append_duration`	number; default: 10
`upload_audio_format`	string; options: wav, mp3, aac, flac; default: wav

Related Models

mirelo/sfx1.6/inpaint-audio
mirelo/sfx1.6/text-to-audio
mirelo/sfx1.6/video-to-video