ace_step_1.5_sft The quality tier — tighter lyric adherence, more sampler control.
No GPU. No setup. Cancel anytime.
ACE-Step 1.5 SFT runs the same model with a fifty-step schedule, finer guidance control, and the er_sde sampler — the tier to use when the vocal needs to land every word.
The fuller schedule costs several times more than Turbo, but a 30-second track is still only about two and a half cents.
On the Sogni API you pay per track in Spark (1 Spark = $0.005). Prefer a flat rate? The Sogni app runs ACE-Step 1.5 SFT and 100+ other models credit-free under fair use.
| Configuration | Spark | USD |
|---|---|---|
| 30 s · 50 steps | 4.87 Spark | $0.024 |
| 3 min · 50 steps | 29.2 Spark | $0.15 |
One Sogni API key reaches every model on the Supernet — call ACE-Step 1.5 SFT by id.
import { SogniClient } from '@sogni-ai/sogni-client';
const client = await SogniClient.createInstance({
appId: crypto.randomUUID(),
apiKey: process.env.SOGNI_API_KEY,
network: 'fast',
});
const project = await client.projects.create({
type: 'audio',
modelId: 'ace_step_1.5_sft',
positivePrompt: 'dreamy synthwave with a warm bassline',
lyrics: undefined, // omit for instrumental
numberOfMedia: 1,
duration: 30,
});
const [url] = await project.waitForCompletion();
console.log(url); // result link — download within 24hcurl https://api.sogni.ai/v1/creative-agent/workflows \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $SOGNI_API_KEY" \
-d '{
"input": {
"title": "First render",
"steps": [{
"id": "step1",
"toolName": "generate_music",
"arguments": { "prompt": "dreamy synthwave with a warm bassline", "model": "sft", "duration": 30 }
}]
},
"confirm_cost": true
}' REST workflow alias: sft. Pin the exact id with the SDK. Full reference at docs.sogni.ai.
Most platforms ration credits or rent a cloud GPU by the hour. Sogni gives you a flat monthly price for credit-free fair-use generation, powered by a creator-owned GPU network — or per-render Spark pricing if you'd rather pay as you go via the API.
One flat price in the app. Generate under fair use without a per-image meter.
Image, video, music, and language models in one workspace and one API key.
Prefer pay-as-you-go? Call ACE-Step 1.5 SFT by id and pay in Spark.
Runs on a decentralized GPU network where workers share subscription revenue.
ACE-Step 1.5 SFT runs the same model with a fifty-step schedule, finer guidance control, and the er_sde sampler — the tier to use when the vocal needs to land every word.
From 4.87 Spark ($0.024) per track on the Sogni API (1 Spark = $0.005) — or unlimited under fair use on a flat monthly Sogni plan.
Create instantly in the Sogni app, or call the Sogni API with model id ace_step_1.5_sft.
No. ACE-Step 1.5 SFT runs on the Sogni Supernet — a decentralized network of creator GPUs — with no local install or graphics card required.
Create in the app, or build with the API. Your call.