Ace Step Audio Inpaint

Ace Step Audio Inpaint

Playground

ACE-Step Audio Inpaint edits a specific audio segment to change lyrics or style while preserving the surrounding audio. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

ACE-Step Audio Inpaint is a powerful music and audio editing model developed by WaveSpeedAI. It enables precise, intelligent modification of selected time ranges within an existing audio clip — perfect for fixing, remixing, or creatively reimagining tracks without re-generating the whole piece.

Key Features

• Precise Segment Editing: Modify only the section you want — define start and end times to edit exactly the range you need.
• Seamless Audio Blending: New content merges naturally with surrounding audio for smooth, undetectable transitions.
• Flexible Timing Control: Choose whether your start or end times are relative to the beginning or end of the track.
• Style & Lyric Adaptability: Add new instrumentation, effects, or lyrics while preserving the overall flow and tone.
• Controlled Variation: Adjust how much the regenerated section diverges from the original using seed and creative parameters.

Parameters

Use Cases

• Repair or refine — Fix errors or off-beat moments in specific sections.
• Rewrite lyrics — Try new vocal phrasing or emotional tone.
• Remix segments — Replace or restyle a part of a song without altering the rest.
• Audio storytelling — Modify voiceovers or sound effects within a fixed-length clip.

Pricing

Total cost = duration of uploaded audio (in seconds) × $0.0002

Examples

• 30s audio → 30 × $0.0002 = $0.006
• 60s audio → 60 × $0.0002 = $0.012
• 3 min (180s) audio → 180 × $0.0002 = $0.036

Notes

• Pricing is based on the total duration of the source audio file, not the edited segment length.
• Ensure uploaded audio URLs are publicly accessible.
• Please ensure your content complies with usage guidelines.

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",
  "tags": "example",
  "start_time_relative_to": "start",
  "start_time": 0,
  "end_time_relative_to": "start",
  "end_time": 30,
  "seed": -1
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/ace-step/audio-inpaint" \
  -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