WaveSpeedAI APIWavespeed AIAce Step Audio Outpaint

Ace Step Audio Outpaint

Ace Step Audio Outpaint

Playground

Try it on WavespeedAI!

ACE-Step Audio Outpaint generates seamless start or end extensions that match the original, ideal for intros, outros and longer tracks. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

ace-step/audio-outpaint 🎵

ACE-Step Audio Outpaint is an intelligent music extension model from WaveSpeedAI that seamlessly expands existing audio tracks — adding new intros, outros, or transitions while keeping the same rhythm, tone, and emotion.


🌟 Key Features

  • 🎧 Extend Before or After Add new audio segments before the beginning or after the end of your original clip.

  • 🎶 Natural Transitions Newly generated audio blends smoothly with the existing material — no abrupt changes or mismatched tones.

  • 🕒 Flexible Duration Extend by any length up to 4 minutes, perfect for building full-length versions or looping tracks.

  • 🎼 Style & Theme Control Use tags (like lofi, hiphop, drum and bass, trap, chill) to define the musical direction of the extension.

  • 🔁 Creative Consistency Keeps harmony, rhythm, and production style consistent with the original track.


⚙️ Parameters

ParameterDescription
audio*Upload or link to an existing audio file (MP3 / WAV).
tags*Describe the desired genre or mood of the extended section.
extend_before_durationDuration (in seconds) to generate before the start of the original audio.
extend_after_durationDuration (in seconds) to generate after the end of the original audio.
lyrics(Optional) Add or modify lyrics for the new section.
seedControl randomness — use fixed seeds for reproducibility, -1 for variation.

💡 Use Cases

  • 🎵 Add custom intros — Build a thematic or ambient start for your track.
  • 🎚 Create extended mixes — Add smooth endings or looping sections for DJ sets.
  • 🎧 Lengthen instrumentals — Extend beats or melodic sections for performance or remixing.
  • 🎬 Audio production & film — Stretch soundscapes and background tracks for cinematic timing.

💰 Pricing

MetricPrice
Per second of generated audio$0.0002 / s

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result


# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/ace-step/audio-outpaint" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "extend_before_duration": 0,
    "extend_after_duration": 30,
    "lyrics": "",
    "seed": -1
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"

Parameters

Task Submission Parameters

Request Parameters

ParameterTypeRequiredDefaultRangeDescription
audiostringYes--Audio file to transcribe. Provide an HTTPS URL or upload a file (MP3, WAV, FLAC up to 60 minutes).
tagsstringYes--Comma-separated list of genre tags to control the style.
extend_before_durationnumberNo-0 ~ 240Duration to extend from the start in seconds.
extend_after_durationnumberNo300 ~ 240Duration to extend from the end in seconds.
lyricsstringNo--Vocal content for generation. Use [inst] or [instrumental] for no vocals.
seedintegerNo-1-1 ~ 2147483647The random seed for reproducibility.

Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
data.idstringUnique identifier for the prediction, Task Id
data.modelstringModel ID used for the prediction
data.outputsarrayArray of URLs to the generated content (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.has_nsfw_contentsarrayArray of boolean values indicating NSFW detection for each output
data.statusstringStatus of the task: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds

Result Request Parameters

© 2025 WaveSpeedAI. All rights reserved.