Stable Audio 3 Text-to-Audio is a fast AI audio generation model that creates sound effects from text prompts with controllable duration and output format. Ready-to-use REST inference API for sound effect generation, ambient audio, game audio, video production, cinematic sound design, creator content, and professional text-to-audio workflows with simple integration, no coldstarts, and affordable pricing.
Idle
$0.0206per run·~48 / $1
30-second cinematic sound-design scene: an isolated desert gas station at midnight with buzzing fluorescent lights, distant highway wind, a loose metal sign creaking, insects around the lamps, and a faraway truck passing slowly. Keep it detailed, spatial, realistic, and non-musical.
Stability AI Stable Audio 3 Text-to-Audio generates audio directly from a natural-language prompt, with controls for duration, negative prompting, inference steps, guidance scale, and output format. It is suitable for sound design, ambient scenes, cinematic textures, audio prototyping, and other prompt-driven audio generation workflows.
Prompt-based audio generation
Generate audio from a text description of mood, environment, texture, or sound event.
Duration control
Choose how long the generated audio should be.
Negative prompt support
Use negative_prompt to steer the model away from unwanted elements.
Generation controls
Adjust num_inference_steps and guidance_scale to balance fidelity, control, and generation behavior.
Flexible output format
Export the generated audio in a supported format such as mp3.
Production-ready API
Suitable for sound effects, ambience, cinematic scenes, creative prototyping, and audio ideation workflows.
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text prompt describing the audio you want to generate. |
| duration | No | Output audio duration in seconds. |
| negative_prompt | No | Text description of sounds or qualities you want to avoid. |
| num_inference_steps | No | Number of inference steps used during generation. |
| guidance_scale | No | Controls how strongly the model follows the prompt. |
| output_format | No | Output audio format, such as mp3. |
num_inference_steps and guidance_scale if needed.30-second cinematic sound-design scene: an isolated desert gas station at midnight with buzzing fluorescent lights, distant highway wind, a loose metal sign creaking, insects around the lamps, and a faraway truck passing slowly. Keep it detailed, spatial, realistic, and non-musical.
Just $0.0206 per generation.
duration, negative_prompt, num_inference_steps, guidance_scale, and output_format do not affect pricingnegative_prompt when you want to suppress music, vocals, distortion, or unwanted artifacts.num_inference_steps if you want potentially more refined output and can tolerate more runtime.guidance_scale when you want tighter prompt adherence.prompt is required.Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/stability-ai/stable-audio-3/text-to-audio with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Stable Audio 3 Text To Audio below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"duration": 30,
"num_inference_steps": 8,
"guidance_scale": 1,
"output_format": "mp3"
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/stability-ai/stable-audio-3/text-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/text-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 ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"duration": 30,
"num_inference_steps": 8,
"guidance_scale": 1,
"output_format": "mp3"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
`https://api.wavespeed.ai/api/v3/predictions/${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 = {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"duration": 30,
"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/text-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 Text To Audio is a Stability AI model for audio generation, exposed as a REST API on WaveSpeedAI. Stable Audio 3 Text-to-Audio is a fast AI audio generation model that creates sound effects from text prompts with controllable duration and output format. Ready-to-use REST inference API for sound effect generation, ambient audio, game audio, video production, cinematic sound design, creator content, and professional text-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-text-to-audio.
Stable Audio 3 Text To Audio starts at $0.021 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`, `duration`, `guidance_scale`, `num_inference_steps`, `negative_prompt`, `output_format`. 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-text-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.