MiniMax H3 Open Weights | Try in Video Generator →

Stable Audio 3 Audio Outpainting API

stability-ai/

Stable Audio 3 Audio Outpainting is a fast AI audio extension model that extends a source audio clip before or after its existing content. Ready-to-use REST inference API for audio continuation, sound effect extension, ambient audio expansion, music production, game audio, video sound design, and professional audio editing workflows with simple integration, no coldstarts, and affordable pricing.

audio-to-audio
Input

Idle

$0.0446per run·~22 / $1

ExamplesView all

Extend the source with a dark cinematic pulse, low cello drones, muted piano repetitions, subtle analog bass, and distant metallic textures; preserve the tempo and key, then build into a tense new phrase without vocals.

Related Models

README

Stability AI Stable Audio 3 Audio-Outpainting

Stability AI Stable Audio 3 Audio-Outpainting extends an existing audio clip by generating new audio before and/or after the original source. It is designed for audio continuation, intro/outro expansion, ambient bed extension, scene transitions, and other prompt-guided audio editing workflows.

Why Choose This?

  • Audio extension in both directions
    Add newly generated audio before the source clip, after it, or on both sides.

  • Prompt-guided outpainting
    Use a text prompt to describe how the new extension audio should sound.

  • Negative prompt support
    Add negative_prompt to reduce unwanted elements or steer away from specific sounds.

  • Flexible extension length
    Independently control how many seconds to extend before and after the source audio.

  • Generation controls
    Adjust num_inference_steps and guidance_scale for more control over output behavior.

  • Multiple export formats
    Export results in mp3, wav, flac, ogg, opus, m4a, or aac.

Parameters

ParameterRequiredDescription
audioYesSource audio to extend.
promptYesText prompt describing the extension audio.
extend_seconds_beforeNoSeconds to extend before the original audio. Range: 0–380. Default: 0.
extend_seconds_afterNoSeconds to extend after the original audio. Range: 0–380. Default: 5.
negative_promptNoOptional terms to avoid in the generated audio.
num_inference_stepsNoNumber of inference steps. Range: 1–100. Default: 8.
guidance_scaleNoPrompt guidance strength. Range: 0–25. Default: 1.
output_formatNoOutput audio format. Supported values: mp3, wav, flac, ogg, opus, m4a, aac. Default: mp3.

How to Use

  1. Upload your source audio — provide the clip you want to extend.
  2. Write your prompt — describe the sound, mood, texture, or continuation style you want.
  3. Set extension length — choose how many seconds to generate before and/or after the source clip.
  4. Add a negative prompt (optional) — list sounds or qualities you want to avoid.
  5. Adjust generation controls (optional) — tune num_inference_steps and guidance_scale if needed.
  6. Choose output format — select the format that best fits your workflow.
  7. Submit — run the model and download the outpainted audio.

Example Prompt

Extend this ambient desert night recording with distant wind, subtle metallic creaks, low environmental rumble, and a natural cinematic continuation.

Pricing

Just $0.0446 per request.

Billing Rules

  • Each outpainting request costs $0.0446
  • Pricing is fixed per request
  • extend_seconds_before, extend_seconds_after, negative_prompt, num_inference_steps, guidance_scale, and output_format do not affect pricing

Best Use Cases

  • Intro extension — Add a lead-in before an existing audio clip.
  • Outro extension — Continue a clip naturally after the original ending.
  • Ambient expansion — Extend environmental or atmospheric recordings.
  • Scene transitions — Build smoother audio bridges before or after a source segment.
  • Creative audio editing — Explore alternate continuations around an existing sound bed.

Pro Tips

  • Use a prompt that matches the tone and texture of the original audio for smoother blending.
  • Extend only as much as needed when continuity matters.
  • Use negative_prompt when you want to avoid music, vocals, distortion, or unwanted effects.
  • Increase num_inference_steps if you want potentially more refined results and can tolerate more runtime.
  • Choose lossless formats like wav or flac when you plan further editing.

Notes

  • audio and prompt are required.
  • extend_seconds_before and extend_seconds_after control how much new audio is generated around the original clip.
  • The original uploaded audio remains the center reference for the final result.
  • Pricing is fixed at $0.0446 per request.

Related Models

  • Stability AI Stable Audio 3 Text-to-Audio — Generate audio directly from a text prompt.
  • Other audio extension workflows — Useful when you want continuation-style generation with different controls or pricing.
  • Audio editing and sound design workflows — Useful when you need localized regeneration or more specialized post-processing.
Note:This website uses AI models provided by third parties.

Stable Audio 3 Audio Outpainting API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/stability-ai/stable-audio-3/audio-outpainting with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Stable Audio 3 Audio Outpainting below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "extend_seconds_before": 0,
    "extend_seconds_after": 5,
    "num_inference_steps": 8,
    "guidance_scale": 1,
    "output_format": "mp3"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/stability-ai/stable-audio-3/audio-outpainting" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d "$REQUEST_BODY")

TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "$TASK" | jq -r '.urls.get // empty')
if [ -z "$RESULT_URL" ]; then
  RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
    -H "Authorization: Bearer $WAVESPEED_API_KEY")
  RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
  STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
  case "$STATUS" in
    completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
  esac
done
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/stability-ai/stable-audio-3/audio-outpainting";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');

async function requestJson(url, options = {}) {
  const response = await fetch(url, options);
  if (!response.ok) throw new Error(await response.text());
  return response.json();
}

// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "extend_seconds_before": 0,
        "extend_seconds_after": 5,
        "num_inference_steps": 8,
        "guidance_scale": 1,
        "output_format": "mp3"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;

// 2. Poll until the prediction finishes.
while (true) {
  const resultBody = await requestJson(resultUrl, {
    headers: { "Authorization": `Bearer ${apiKey}` },
  });
  const result = resultBody.data ?? resultBody;
  if (result.status === "completed") {
    console.log(result.outputs);
    break;
  }
  if (["failed", "cancelled", "timeout"].includes(result.status)) throw new Error(JSON.stringify(result));
  if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
  await new Promise(resolve => setTimeout(resolve, 2000));
}
Python example
import json
import os
import time
from urllib.request import Request, urlopen

api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
    "audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "extend_seconds_before": 0,
    "extend_seconds_after": 5,
    "negative_prompt": "",
    "num_inference_steps": 8,
    "guidance_scale": 1,
    "output_format": "mp3"
}

def request_json(url, data=None):
    request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
    with urlopen(request) as response:
        return json.load(response)

# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/stability-ai/stable-audio-3/audio-outpainting", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
    raise RuntimeError("Submission response did not contain a prediction id")
result_url = task.get("urls", {}).get("get") or f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"

# 2. Poll until the prediction finishes.
while True:
    result_body = request_json(result_url)
    result = result_body.get("data", result_body)
    status = result.get("status")
    if status == "completed":
        print(result.get("outputs", []))
        break
    if status in {"failed", "cancelled", "timeout"}:
        raise RuntimeError(result)
    if status not in {"created", "processing"}:
        raise RuntimeError(f"Unexpected status: {status}")
    time.sleep(2)

Stable Audio 3 Audio Outpainting API — Frequently asked questions

What is the Stable Audio 3 Audio Outpainting API?

Stable Audio 3 Audio Outpainting is a Stability AI model for AI inference, exposed as a REST API on WaveSpeedAI. Stable Audio 3 Audio Outpainting is a fast AI audio extension model that extends a source audio clip before or after its existing content. Ready-to-use REST inference API for audio continuation, sound effect extension, ambient audio expansion, music production, game audio, video sound design, and professional audio editing workflows with simple integration, no coldstarts, and affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Stable Audio 3 Audio Outpainting API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/stability-ai/stability-ai-stable-audio-3-audio-outpainting.

How much does Stable Audio 3 Audio Outpainting cost per run?

Stable Audio 3 Audio Outpainting starts at $0.045 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Stable Audio 3 Audio Outpainting accept?

Key inputs: `prompt`, `audio`, `guidance_scale`, `num_inference_steps`, `negative_prompt`, `extend_seconds_after`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/stability-ai/stability-ai-stable-audio-3-audio-outpainting.

How do I get started with the Stable Audio 3 Audio Outpainting API?

Sign up for a free WaveSpeedAI account to claim starter credits, copy your API key from /accesskey, then call the endpoint shown in the API tab of the playground. The playground also auto-generates a code sample in Python, JavaScript, or cURL for the parameters you've set.

Can I use Stable Audio 3 Audio Outpainting outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (Stability AI). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.

Stable Audio 3 Audio Outpainting API on WaveSpeedAI