Mirelo SFX 2.0 Text-to-Audio generates sound effects and ambience from text descriptions, with positive and negative prompt controls, configurable duration, and one audio output per request for sound design, video production, games, ads, and creative audio workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
$0.016per run·~62 / $1
A massive alien spacecraft flies directly overhead. A distant low engine rumble rapidly approaches, swelling into a powerful, textured turbine roar and rushing wind as the ship passes close above the listener at the midpoint. The engine pitch drops sharply with a clear Doppler shift, then quickly recedes into the distance. One continuous flyby, realistic cinematic sound design, spacious outdoor acoustics.
Mirelo SFX 2.0 Text-to-Audio generates sound effects and ambience directly from text descriptions. Describe the sound you want, use an optional negative prompt to exclude unwanted elements, choose the duration and audio format, and generate a finished audio track.
It is designed for game audio, cinematic sound design, environmental ambience, Foley-style effects, and other non-speech audio workflows.
Text-to-sound generation
Create sound effects and ambience directly from natural-language descriptions.
Positive and negative guidance
Describe both what should be present and what should be avoided in the generated audio.
Flexible duration
Generate audio from 0.1 seconds up to 600 seconds.
Multiple output formats
Export as wav, mp3, aac, or flac.
Bitrate control
Configure bitrate for MP3 and AAC when specific encoding requirements matter.
Seed support
Use a fixed seed when reproducibility is useful.
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the sound effects or ambience to generate. Maximum 2000 characters. |
| negative_prompt | No | Optional description of sounds or elements to avoid. Maximum 1000 characters. |
| duration | No | Requested audio duration in seconds. Range: 0.1–600. Default: 30. |
| audio_bitrate_kbps | No | Optional target bitrate for MP3 or AAC output. Omit for automatic encoding. |
| output_format | No | Output audio format: wav, mp3, aac, or flac. Default: wav. |
| seed | No | Optional integer seed from 0 to 2147483647. Omit for random generation. |
0.1 to 600 seconds.wav, mp3, aac, or flac.Pricing is based on the requested duration.
The rate is $0.016 per requested second.
| Duration | Price |
|---|---|
| 1s | $0.016 |
| 5s | $0.080 |
| 10s | $0.160 |
| 30s | $0.480 |
| 60s | $0.960 |
| 600s | $9.600 |
negative_prompt, output_format, audio_bitrate_kbps, and seed do not add separate charges.
negative_prompt to reduce unwanted music, speech, voices, or background elements.wav or flac when lossless output is preferred.seed when comparing prompt or parameter changes.prompt is required and supports up to 2000 characters.negative_prompt supports up to 1000 characters.duration supports 0.1–600 seconds and defaults to 30.output_format defaults to wav.wav, mp3, aac, and flac.audio_bitrate_kbps empty for WAV and FLAC.32, 40, 48, 56, 64, 80, 96, 112, 128, 160, 192, 224, 256, or 320 kbps.32 to 256 kbps; actual encoded bitrate may be lower.256 kbps target.Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/mirelo-ai/sfx-2.0/text-to-audio with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Sfx 2.0 Text To Audio below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"duration": 30,
"output_format": "wav"
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/mirelo-ai/sfx-2.0/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="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(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' "$RESULT" | jq '.outputs'; break ;;
failed|cancelled|timeout|deleted) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
*) sleep 2 ;;
esac
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/mirelo-ai/sfx-2.0/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 ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"duration": 30,
"output_format": "wav"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${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", "deleted"].includes(result.status)) throw new Error(JSON.stringify(result));
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,
"output_format": "wav"
}
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/mirelo-ai/sfx-2.0/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 = 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", "deleted"}:
raise RuntimeError(result)
time.sleep(2)Sfx 2.0 Text To Audio is a Mirelo Ai model for sound effect generation, exposed as a REST API on WaveSpeedAI. Mirelo SFX 2.0 Text-to-Audio generates sound effects and ambience from text descriptions, with positive and negative prompt controls, configurable duration, and one audio output per request for sound design, video production, games, ads, and creative audio workflows. Ready-to-use REST inference API, best performance, no coldstarts, 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 Python, JavaScript, and cURL examples for submitting requests and polling results. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/mirelo-ai/mirelo-ai-sfx-2.0-text-to-audio.
Sfx 2.0 Text To Audio starts at $0.016 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`, `seed`, `negative_prompt`, `audio_bitrate_kbps`, `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/mirelo-ai/mirelo-ai-sfx-2.0-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 (Mirelo Ai). Check the provider's applicable terms and WaveSpeedAI's Terms of Service before commercial use.