models/ACE Step/Ace Step Prompt To Audio

Ace Step Prompt To Audio

music

Ace Step Prompt To Audio (ace-step/ace-step-prompt-to-audio) is a music model from ACE Step. Pricing via AIgateway: $0.0002 per second. Call it via https://api.aigateway.sh/v1/audio/music — set model="ace-step/ace-step-prompt-to-audio". Best for: Background tracks, Game scores, Ad jingles.

slug · ace-step/ace-step-prompt-to-audioprovider · ACE Step

Use this model

model: ace-step/ace-step-prompt-to-audio
curl https://api.aigateway.sh/v1/audio/music \
  -H "Authorization: Bearer $AIGATEWAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"ace-step/ace-step-prompt-to-audio","prompt":"lo-fi piano with light rain","duration":15}'

Capabilities

Strengths

  • Full-track generation
  • Lyric-aware composition

Use cases

Background tracksGame scoresAd jingles

Pricing

Per video second$0.0002
You pay pass-through · 5% applied at credit top-up, not per-call.
Try in playground →CompareAPI referenceSee usage ranking →

Collections

More text models →More from ACE Step →Frontier models →Free-tier models →
API schema

Call Ace Step Prompt To Audio from any OpenAI SDK

POST https://api.aigateway.sh/v1/audio/music·Content-Type: application/json·Auth: Bearer sk-aig-...

Request body

json
{
  "model": "ace-step/ace-step-prompt-to-audio",
  "prompt": "Lo-fi hip-hop with vinyl crackle and warm Rhodes piano",
  "lyrics": "Optional — leave empty for instrumental",
  "duration": 30,         // seconds
  "format": "mp3"         // mp3 | wav
}

// Response is an async job — poll /v1/jobs/<id> until status === "completed".

Response

json
{
  "id": "job_abc123",
  "status": "queued",
  "model": "ace-step/ace-step-prompt-to-audio",
  "created": 1776947082
}

// After completion:
{
  "id": "job_abc123",
  "status": "completed",
  "result": {
    "url": "https://media.aigateway.sh/music/abc123.mp3",
    "duration": 30
  }
}

Quickstart

# See docs at https://aigateway.sh/docs

Errors

401authentication_errorInvalid or missing API key
402insufficient_creditsWallet empty (PAYG only)
404not_foundUnknown model or endpoint
429rate_limit_errorOver per-minute limit — see Retry-After header
500server_errorUpstream provider failed (retryable)
503service_unavailableUpstream saturated (retryable)
Full docs →API reference →OpenAPI spec →llms.txt →

Frequently asked questions

What is Ace Step Prompt To Audio?
It is a music model from ACE Step, accessible via AIgateway's OpenAI-compatible API at slug ace-step/ace-step-prompt-to-audio.
How much does Ace Step Prompt To Audio cost via AIgateway?
Pass-through pricing plus a 5% platform fee applied at top-up. See the pricing panel on this page for exact rates.
How do I call Ace Step Prompt To Audio from my code?
Point the OpenAI SDK at https://api.aigateway.sh/v1 with your AIgateway key and set model to "ace-step/ace-step-prompt-to-audio". The request and response shapes match OpenAI exactly.
Does Ace Step Prompt To Audio support streaming, tool calling, vision, and JSON mode?
Streaming — no. Tool calling — no. Vision — no. JSON mode — no. Prompt caching — no.
What are the best use cases for Ace Step Prompt To Audio?
Background tracks, Game scores, Ad jingles. Key strengths: Full-track generation; Lyric-aware composition.
Can I bring my own ACE Step API key (BYOK)?
Yes. Attach a ACE Step key in your AIgateway dashboard and this model flips to pass-through — you pay ACE Step directly and AIgateway waives the 5% platform fee on those calls.