Skip to navigation

ACE-Step 1.5 XL

ACE-Step 1.5 XL
ACE-Step · Audio Generation
POST /v1/audio/generations

Open-source music generation model for text-to-song and lyric-guided audio, with fast 8-step XL Turbo inference for controllable song iteration.

See ACE-Step 1.5 XL pricing and specs or try it in the Playground.

At a glance

FieldValue
Model idace-step-1-5-xl
Model release date2026-04-02
Input modalitiesText
Output modalitiesAudio
Context window-
Weight precisionBF16
Featuresmusic_generation, lyrics, text_to_music, seed_control, commercial_ready
Native inferenceYes
NewNo
Supported endpointsPOST /v1/audio/generations
Alternate model idsace-step-1.5-xl, ace-step/acestep-v15-xl-turbo

Pricing

ChargeSpecRate
Music generationper generated second$0.0003 $0.00025

Example request

curl https://api.empiriolabs.ai/v1/audio/generations \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H 'Content-Type: application/json' \
-d '{"model": "ace-step-1-5-xl", "prompt": "warm jazz piano", "audio_duration": 10}'

Parameters

ParameterTypeRequiredDefaultDescription
promptstringyes-Genre, mood, instrumentation, and BPM hints describing the music to compose. Comma-separated tags work well.
lyricsstringno-Vocal lyrics for the track. Use [verse] / [chorus] / [bridge] tags to mark sections, blank line for instrumental break. Leave empty for purely instrumental tracks.
audio_durationnumberno30.0Length of the generated track in seconds, from 10 to 600. · Range: 10.0 – 600
num_inference_stepsintegerno8Number of diffusion steps. 8 is recommended for this Turbo model; more steps add polish, fewer steps give faster drafts. · Range: 1 – 20
guidance_scalenumberno1.0Classifier-free guidance scale. 1.0 follows the model’s natural distribution; higher values push closer to the prompt at the cost of variety. · Range: 0.0 – 20.0
shiftnumberno-Diffusion timestep shift. Default leaves the schedule unchanged; nudge to 1.0+ for shorter/punchier or below 1.0 for slower/dreamier results.
seedintegerno-Random seed for reproducibility. Same seed + identical params produces the same track.
formatenumno"flac"Audio file format. FLAC is lossless, WAV is uncompressed, and OGG and MP3 are smaller lossy files. · Allowed: flac, wav, ogg, mp3
response_formatenumno"url"Return a signed media URL by default, or base64 JSON when requested. · Allowed: url, b64_json
return_base64booleannofalseCompatibility alias for response_format=b64_json.

Notes

Defaults

  • 8 inference steps
  • Guidance scale 1.0
  • Lossless FLAC output

Controls

Supports lyrics, prompt/description, 10-600s duration, seed, shift, and URL or base64 output mode.


Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/ace-step-1-5-xl.