stability-ai/stable-audio/open

Name: Stable Audio Open
Author: stability-ai

Stable Audio Open is stability-ai's AI audio generation model. Produce high-quality music tracks, sound effects, and audio landscapes from natural language prompts.

Input

Prompt(string)

The prompt to generate audio from

Seconds Start(integer)

047

The start point of the audio clip to generate Range: 0 to 47.

Seconds Total(integer)

047

The duration of the audio clip to generate Range: 0 to 47.

Steps(integer)

21000

The number of steps to denoise the audio for Range: 2 to 1000.

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 IDstability-ai/stable-audio/open

Input Schema

4 parameters · 1 required · 3 optional

Parameter	Type	Required	Description
`prompt`	string	Required	The prompt to generate audio from
`steps`	integer	Optional	The number of steps to denoise the audio for · Min: 2 · Max: 1000 · Default: 100
`seconds_start`	integer	Optional	The start point of the audio clip to generate · Min: 0 · Max: 47 · Default: 0
`seconds_total`	integer	Optional	The duration of the audio clip to generate · Min: 0 · Max: 47 · Default: 30

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": "stability-ai/stable-audio/open",
  "steps": 100,
  "prompt": "128 BPM tech house drum loop",
  "seconds_start": 0,
  "seconds_total": 30
}'

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

← Back to Stable Audio Open

API README

Stable Audio Open

Stable Audio Open occupies a clearly bounded position in a audio production pipeline under the route stability-ai/stable-audio/open. It is best evaluated as a named workflow endpoint rather than as a generic substitute for neighboring versions: planners can assign the route to a specific brief, record the chosen revision, and keep approval history tied to one predictable integration surface from intake through delivery.

A practical rollout of Stable Audio Open should begin with source-readiness checks, ownership of the submitted material, an agreed budget, and a written definition of the final open deliverable. Before automation is enabled, the acceptance pass should verify that the returned asset opens correctly, fits the intended downstream toolchain, satisfies the project’s review criteria, and can be reproduced from the stored request and route identity stability-ai/stable-audio/open.

Highlights

Distinct output behavior. For Stable Audio Open, for Stable Audio Open, choose where the requested clip begins with seconds_start In Stable Audio Open, this capability is applied through the exact stability-ai/stable-audio/open workflow with steps as a relevant request control; the steps control exposes the corresponding choice in this route; the steps control exposes the corresponding choice in this route.
Creative control. For Stable Audio Open, for Stable Audio Open, set seconds_total up to 47 seconds In Stable Audio Open, this capability is applied through the exact stability-ai/stable-audio/open workflow with prompt as a relevant request control; the prompt control exposes the corresponding choice in this route; the prompt control exposes the corresponding choice in this route.
Workflow fit. For Stable Audio Open, for Stable Audio Open, raise or lower the step count across the declared 2–1,000 range In Stable Audio Open, this capability is applied through the exact stability-ai/stable-audio/open workflow with seconds start as a relevant request control; the seconds start control exposes the corresponding choice in this route; the seconds start control exposes the corresponding choice in this route.
Production detail. For Stable Audio Open, for Stable Audio Open, generate from prompt without an audio input field In Stable Audio Open, this capability is applied through the exact stability-ai/stable-audio/open workflow with seconds total as a relevant request control; the seconds total control exposes the corresponding choice in this route; the seconds total control exposes the corresponding choice in this route.

Pricing

Configuration	Price
Per request	$0.000575

When to Use

Scenario	Why this model fits
Choose Stable Audio Open	Use it when the required deliverable is specifically the audio result documented for `stability-ai/stable-audio/open`.
Match the source material	Select this route when your inputs naturally map to `steps`, `prompt`, `seconds_start`, `seconds_total`.
Use its distinguishing capability	For Stable Audio Open, choose where the requested clip begins with seconds_start In Stable Audio Open, this capability is applied through the exact stability-ai/stable-audio/open workflow with steps as a relevant request control; the steps control exposes the corresponding choice in this route
Plan repeatable production	For Stable Audio Open, set seconds_total up to 47 seconds In Stable Audio Open, this capability is applied through the exact stability-ai/stable-audio/open workflow with prompt as a relevant request control; the prompt control exposes the corresponding choice in this route
Confirm cost and delivery	Use the pricing combinations below and the output contract above when budgeting or automating Stable Audio Open jobs.

Prompt Guide

Build the request around the exact stability-ai/stable-audio/open schema. Start with required fields, then add only the controls needed for the intended output; keep URLs reachable and enum values exactly as shown in Technical Specs.

{
  "prompt": "128 BPM tech house drum loop",
  "steps": 100,
  "seconds_start": 0,
  "seconds_total": 30
}

Technical Specs

Specification	Value
Model ID	`stability-ai/stable-audio/open`
Execution mode	`async`
Required inputs	`prompt`
Request fields	`steps` (integer, optional, min 2, max 1000); `prompt` (string, required); `seconds_start` (integer, optional, min 0, max 47); `seconds_total` (integer, optional, min 0, max 47)
Output	`url` (string); `content_type` (string)