Mirelo SFX1.6 Inpaint Audio is a fast AI audio inpainting model that regenerates a selected segment of a short audio clip while preserving the audio outside that region. Ready-to-use REST inference API for sound effect repair, audio cleanup, segment regeneration, game audio, video production, cinematic sound design, and professional audio editing workflows with simple integration, no coldstarts, and affordable pricing.
Idle

$0.01per run·~100 / $1
Mirelo AI SFX 1.6 Inpaint Audio regenerates a selected segment inside an existing audio clip while preserving the audio before and after that region. It is designed for audio repair, sound replacement, creative audio editing, and localized sound redesign workflows where you want to rewrite only part of a clip instead of regenerating the whole file.
Segment-level audio editing Regenerate only a selected section of an audio clip while keeping the rest unchanged.
Prompt-guided inpainting Add an optional text prompt to guide how the selected region should be regenerated.
Multiple variations
Generate up to 4 inpainted variations in one request with num_samples.
Preserves surrounding audio Audio outside the selected inpaint segment remains intact.
Production-ready workflow Useful for sound repair, effect replacement, music cleanup, and creative segment editing.
| Parameter | Required | Description |
|---|---|---|
| audio | Yes | Source audio clip. Maximum duration is 10 seconds. Audio outside the selected segment is preserved. |
| start_s | Yes | Start of the inpaint region in seconds. Must leave a 1 second left gap. Default: 2. |
| end_s | Yes | End of the inpaint region in seconds. The segment span must be 1–8 seconds. Default: 6. |
| prompt | No | Optional text prompt guiding the regenerated segment. |
| num_samples | No | Number of variations to generate. Range: 1–4. Default: 1. |
start_s and end_s to define the segment you want to regenerate.1 to 4.Replace this section with a darker cinematic ambience, soft low rumble, subtle tension, and cleaner transition into the following audio.
Pricing is based on the inpainted segment length and number of samples.
| Inpaint Length | 1 Sample | 2 Samples | 3 Samples | 4 Samples |
|---|---|---|---|---|
| 1s | $0.01 | $0.02 | $0.03 | $0.04 |
| 2s | $0.02 | $0.04 | $0.06 | $0.08 |
| 4s | $0.04 | $0.08 | $0.12 | $0.16 |
| 6s | $0.06 | $0.12 | $0.18 | $0.24 |
| 8s | $0.08 | $0.16 | $0.24 | $0.32 |
prompt does not affect pricingnum_samples when you want to compare multiple replacement options.audio, start_s, and end_s are required.10 seconds.1 and 8 seconds.start_s must leave at least 1 second of audio before the edited region.Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/mirelo-ai/sfx-1.6/inpaint-audio with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Sfx 1.6 Inpaint Audio below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
"start_s": 2,
"end_s": 6,
"num_samples": 1
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/mirelo-ai/sfx-1.6/inpaint-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/mirelo-ai/sfx-1.6/inpaint-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 ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
"start_s": 2,
"end_s": 6,
"num_samples": 1
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
`https://api.wavespeed.ai/api/v3/predictions/${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",
"start_s": 2,
"end_s": 6,
"num_samples": 1
}
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-1.6/inpaint-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)Sfx 1.6 Inpaint Audio is a Mirelo Ai model for AI inference, exposed as a REST API on WaveSpeedAI. Mirelo SFX1.6 Inpaint Audio is a fast AI audio inpainting model that regenerates a selected segment of a short audio clip while preserving the audio outside that region. Ready-to-use REST inference API for sound effect repair, audio cleanup, segment regeneration, game audio, video production, cinematic 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.
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/mirelo-ai/mirelo-ai-sfx-1.6-inpaint-audio.
Sfx 1.6 Inpaint Audio starts at $0.010 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`, `end_s`, `num_samples`, `start_s`. 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-1.6-inpaint-audio.
Median end-to-end generation time on WaveSpeedAI is around 7 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.
Commercial usage rights depend on the model's license, set by its provider (Mirelo Ai). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.