Mirelo AI Sfx 1.6 Inpaint Audio API Documentation

Mirelo AI Sfx 1.6 Inpaint Audio API Documentation

Playground

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.

Features

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.

Why Choose This?

• 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.

Parameters

How to Use

1. Upload your audio — provide the source audio clip you want to edit.
2. Set the inpaint region — choose start_s and end_s to define the segment you want to regenerate.
3. Add a prompt (optional) — describe the sound, mood, or style you want for the regenerated segment.
4. Set number of samples — choose how many variations you want, from 1 to 4.
5. Submit — run the model and download the inpainted audio results.

Example Prompt

Replace this section with a darker cinematic ambience, soft low rumble, subtle tension, and cleaner transition into the following audio.

Pricing

Pricing is based on the inpainted segment length and number of samples.

Billing Rules

• Pricing is $0.01 per generated second
• prompt does not affect pricing
• Pricing is based on the regenerated segment only, not the full uploaded audio duration

Best Use Cases

• Audio repair — Replace damaged or unwanted sections inside a clip.
• Sound redesign — Change one localized segment without touching the rest of the recording.
• Music cleanup — Rewrite small regions in intros, drops, transitions, or effects.
• Creative editing — Test alternate versions of a section with multiple generated samples.
• Loop and transition refinement — Improve a specific transition area inside a short clip.

Pro Tips

• Choose the smallest region that needs replacement for more controllable results.
• Use a clear prompt only when you need stronger direction for the regenerated section.
• Keep the source audio clean so the transition into and out of the edited region feels smoother.
• Increase num_samples when you want to compare multiple replacement options.
• Double-check the start and end boundaries so the model edits exactly the intended segment.

Notes

• audio, start_s, and end_s are required.
• Source audio duration must not exceed 10 seconds.
• The inpaint segment span must be between 1 and 8 seconds.
• start_s must leave at least 1 second of audio before the edited region.
• Audio outside the selected inpaint region is preserved.
• Pricing depends on the regenerated segment length and sample count.

Related Models

• Mirelo AI SFX 1.6 Extend Audio — Extend an existing audio clip with newly generated continuation.
• Other Mirelo AI sound generation workflows — Useful when you need full audio generation instead of localized editing.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-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 "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(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' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  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

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters