Ace Step Audio To Audio

Ace Step Audio To Audio

Playground

ACE-Step Audio-to-Audio turns existing tracks into remixes or vocal edits using remix and lyrics modes while preserving audio character. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

ACE-Step Audio-to-Audio is a creative music transformation model that generates new versions of existing tracks. It allows you to remix, rewrite, or restyle a song directly from an uploaded audio file — perfect for producers, remixers, and creators looking to evolve their sound.

✨ Key Features

• 🎛 Remix Mode Change the musical style while preserving rhythm, tempo, and melodic structure. (e.g., turn a pop track into a lo-fi or EDM remix)

• 🎤 Lyrics Mode Edit or replace the song’s vocal content while keeping the instrumental layers intact.

• 🎚 Style Control via Tags Guide generation using genre or mood tags like “jazz,” “cinematic,” “trap,” “ambient chill.”

• 🎵 High Fidelity Preservation Keeps fine-grained acoustic and timbral details from the original audio — ensuring professional-grade sound quality.

• 🪄 Reproducible Outputs Use the seed parameter to reproduce or slightly vary your remix results.

🧩 Parameters

🎶 Use Cases

• Remixing existing tracks into new genres or moods
• Rewriting lyrics while preserving the backing music
• Adapting songs for different campaigns, platforms, or cultural contexts
• Creating A/B variations for music production or content testing
• Expanding music datasets with stylistic diversity

💡 Example Workflows

1. Create a remix: Upload a pop song → set edit_mode: remix → add tags like “synthwave, retro” → generate a new version.

2. Rewrite lyrics: Upload a vocal track → choose edit_mode: lyrics → enter new lyrics → generate a rewritten version keeping rhythm and tone.

💰 Pricing

🎵 Summary

ACE-Step Audio-to-Audio transforms existing music into new creative expressions. Whether you’re remixing genres, rewriting lyrics, or refining mood and tone — it’s your all-in-one AI assistant for dynamic music evolution.

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",
  "original_tags": "example",
  "tags": "example",
  "edit_mode": "remix",
  "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-to-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