text-to-audio
Idle
Your request will cost $0.0002 per run.
For $1 you can run this model approximately 5000 times.
ACE-Step Prompt-to-Audio is an intelligent music generation model that composes full-length audio tracks directly from text prompts. Simply describe the sound you want — from chill jazz to cinematic orchestral — and ACE-Step creates a polished piece in seconds.
Prompt-to-Music Creation Just write your idea in plain language. For example: “A jazzy chillout track with a cozy vibe about rainy evenings in a quiet café.”
Instrumental Mode Toggle the instrumental option to generate music without vocals — perfect for background use, podcasts, or film scoring.
Duration Control Use the slider to set your track length — anywhere from a few seconds to full-minute compositions (e.g., 60s).
Seed for Reproducibility Set the seed value to recreate the same song later, or randomize it for unique variations.
Genre & Emotion Understanding The model interprets keywords like “jazzy,” “dark,” “energetic,” “melancholic,” and blends rhythm, instruments, and mood accordingly.
Metric | Price |
---|---|
Per second of generated audio | $0.0002 / s |
ACE-Step Prompt-to-Audio transforms words into music — from short jingles to full-length compositions. It’s your AI-powered music studio, ready to help musicians, creators, and filmmakers bring sound to life with just a sentence.