Text-to-music with lyrics — vocal or instrumental tracks up to 10 minutes, in Turbo and SFT builds.
No GPU. No setup. Cancel anytime.
ACE-Step 1.5 generates high-quality music from text prompts and lyrics — vocal or instrumental tracks up to 10 minutes with fine control over BPM, key, time signature, and style.
Builds trade speed for polish: XL Turbo and 1.5 Turbo run few-step schedules for fast drafts; XL SFT and 1.5 SFT run the full supervised-fine-tuned schedule for the highest fidelity.
ACE-Step 1.5 ships in 4 builds — same family, different speed/quality trade-offs. Pick the variant that fits, or start with the default.
| Variant | Details | From | |
|---|---|---|---|
XL Turbo Fastace_step_1.5_xl_turbo | Duration: 10 s – 10 min Steps: 8 default · 4–16 Tempo: 30 – 300 BPM Lyrics: 52 languages · or instrumental Output: mp3 · flac · wav | 1.08 Spark · $0.0054 | Create → |
XL SFT Qualityace_step_1.5_xl_sft | Duration: 10 s – 10 min Steps: 50 default · 10–200 Guidance: 7 default · 1–15 Tempo: 30 – 300 BPM Lyrics: 52 languages · or instrumental | 6.08 Spark · $0.03 | Create → |
1.5 Turbo Fastace_step_1.5_turbo | Duration: 10 s – 10 min Steps: 8 default · 4–16 Tempo: 30 – 300 BPM Lyrics: 52 languages · or instrumental Output: mp3 · flac · wav | 0.90 Spark · $0.0043 | Create → |
1.5 SFT Qualityace_step_1.5_sft | Duration: 10 s – 10 min Steps: 50 default · 10–200 Guidance: 5 default · 1–15 Tempo: 30 – 300 BPM Lyrics: 52 languages · or instrumental | 4.87 Spark · $0.024 | Create → |
Use pay-as-you-go Spark packs for each track (1 Spark = $0.005), or choose a flat-rate Sogni plan for credit-free fair-use generation in the app.
| Variant / configuration | Spark | USD |
|---|---|---|
| XL Turbo · 30 s · 8 steps | 1.08 Spark | $0.0054 |
| XL Turbo · 3 min · 8 steps | 6.47 Spark | $0.032 |
| XL Turbo · 10 min · 8 steps (max duration 600 s) | 21.6 Spark | $0.11 |
| XL SFT · 30 s · 50 steps | 6.08 Spark | $0.03 |
| XL SFT · 3 min · 50 steps | 36.5 Spark | $0.18 |
| 1.5 Turbo · 30 s · 8 steps | 0.90 Spark | $0.0043 |
| 1.5 Turbo · 3 min · 8 steps | 5.40 Spark | $0.026 |
| 1.5 Turbo · 10 min · 8 steps (max duration 600 s) | 18.0 Spark | $0.087 |
| 1.5 SFT · 30 s · 50 steps | 4.87 Spark | $0.024 |
| 1.5 SFT · 3 min · 50 steps | 29.2 Spark | $0.15 |
One Sogni API key reaches every model on the Supernet — call ACE-Step 1.5 with the exact model id for the variant you want.
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_xl_turbo',
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 24h curl 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": "ace_step_1.5_xl_turbo", "duration": 30 }
}]
},
"confirm_cost": true
}' Example uses ace_step_1.5_xl_turbo. Use any exact model id from the Variants table above. Full reference at docs.sogni.ai.
Real generations from Sogni. Hit Use prompt to open the app with ACE-Step 1.5 selected and the full prompt preloaded.
Use a flat monthly plan for credit-free fair-use generation, or buy Spark packs when pay-as-you-go fits better. Both run on the same creator-owned GPU network.
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 by id and pay with Spark packs.
Runs on a decentralized GPU network where workers share subscription revenue.
Use a Turbo build (XL Turbo or 1.5 Turbo) for fast drafts, and an SFT build (XL SFT or 1.5 SFT) for the highest-fidelity final tracks. XL builds are the newer, larger models.
Create in the app, or build with the API. Your call.