Stable Audio 3 Audio-to-Audio is a fast AI audio transformation model that transforms a source audio clip using a text prompt. Ready-to-use REST inference API for audio style transfer, sound effect transformation, music remixing, creative audio editing, game audio, video sound design, and professional audio-to-audio workflows with simple integration, no coldstarts, and affordable pricing.
Idle
$0.024per run·~41 / $1
downtown dusk neo soul pocket groove
Stability AI Stable Audio 3 Audio-to-Audio transforms an existing audio clip into a new result guided by a natural-language prompt. It is designed for remixing, restyling, sound redesign, mood transfer, and other prompt-driven audio transformation workflows.
Audio transformation workflow
Start from an existing audio clip and transform it into a new result instead of generating from scratch.
Prompt-guided editing Use a text prompt to describe the target sound, mood, texture, or musical direction.
Controllable transformation strength
Adjust init_noise_level to control how strongly the output departs from the source audio.
Negative prompt support
Use negative_prompt to avoid unwanted sounds, textures, or stylistic elements.
Flexible output duration
Choose the target output length up to 120 seconds.
Production-ready API Useful for music restyling, sound design, ambient transformation, and creative audio experimentation.
| Parameter | Required | Description |
|---|---|---|
| audio | Yes | Source audio to transform. |
| prompt | Yes | Text prompt describing how to transform the audio. |
| duration | No | Target audio duration in seconds. Range: 1–120. Default: 30. |
| init_noise_level | No | Controls how strongly the source audio is transformed. Range: 0–1. Default: 0.9. |
| negative_prompt | No | Optional terms to avoid in the generated audio. |
| num_inference_steps | No | Number of inference steps. Range: 1–100. Default: 8. |
| guidance_scale | No | Prompt guidance strength. Range: 0–25. Default: 1. |
| output_format | No | Output audio format. Supported values: mp3, wav, flac, ogg, opus, m4a, aac. Default: mp3. |
init_noise_level to control how far the output moves away from the source.num_inference_steps and guidance_scale if needed.Transform this into a dark cinematic ambient track with deeper low-end texture, distant metallic resonance, slower pacing, and a more atmospheric, spacious mix.
Just $0.024 per request.
duration, init_noise_level, negative_prompt, num_inference_steps, guidance_scale, and output_format do not affect pricinginit_noise_level when you want the result to stay closer to the original audio.init_noise_level when you want a stronger transformation.negative_prompt to suppress unwanted artifacts, vocals, harshness, or specific genres.wav or flac when you plan to do further editing after generation.audio and prompt are required.duration supports 1–120 seconds.init_noise_level controls how strongly the model transforms the input audio.Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/stability-ai/stable-audio-3/audio-to-audio with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Stable Audio 3 Audio To Audio below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"duration": 30,
"init_noise_level": 0.9,
"num_inference_steps": 8,
"guidance_scale": 1,
"output_format": "mp3"
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/stability-ai/stable-audio-3/audio-to-audio" \
-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
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/stability-ai/stable-audio-3/audio-to-audio";
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 ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"duration": 30,
"init_noise_level": 0.9,
"num_inference_steps": 8,
"guidance_scale": 1,
"output_format": "mp3"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
`https://api.wavespeed.ai/api/v3/predictions/${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));
}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",
"duration": 30,
"init_noise_level": 0.9,
"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-to-audio", 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 To Audio is a Stability AI model for AI inference, exposed as a REST API on WaveSpeedAI. Stable Audio 3 Audio-to-Audio is a fast AI audio transformation model that transforms a source audio clip using a text prompt. Ready-to-use REST inference API for audio style transfer, sound effect transformation, music remixing, creative audio editing, game audio, video sound design, and professional audio-to-audio workflows with simple integration, no coldstarts, and affordable pricing. You can call it programmatically or try it from the playground above.
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-to-audio.
Stable Audio 3 Audio To Audio starts at $0.024 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.
Key inputs: `prompt`, `audio`, `duration`, `guidance_scale`, `num_inference_steps`, `negative_prompt`. 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-to-audio.
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.
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.