Seedream 5.0 Pro jest już LIVE | Wypróbuj w Generator obrazów →

ACE Step

wavespeed-ai /

ACE-Step generates up to 4-minute music with lyrics from text and high acoustic fidelity; supports voice cloning, lyric edits, and remixing. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

text-to-audio
Wejście

Bezczynny

$0.0002za uruchomienie·~5000 / $1

PrzykładyZobacz wszystkie

Powiązane modele

README

ACE-Step — Text-to-Audio

ACE-Step Text-to-Audio is a next-generation AI music generation model that composes complete songs — including vocals, instrumentals, and lyrics — directly from text descriptions. Produce professional-quality music up to 4 minutes long from simple style tags and optional lyrics.

Why It Stands Out

  • Text-to-music generation: Transform style tags into coherent music tracks with melody, rhythm, and vocals.
  • Style tag control: Enter multiple tags to guide genre, tempo, and energy.
  • Vocal and lyric creation: Generates original vocals and synchronized lyrics that fit your prompt's tone.
  • Fine-grained acoustic fidelity: Maintains dynamic balance, spatial quality, and instrument clarity.
  • Flexible duration: Adjustable from a few seconds to 4 minutes (240 seconds).
  • Reproducibility: Use the seed parameter to recreate exact results.

Parameters

ParameterRequiredDescription
tagsYesList of genres or styles (e.g., lofi, hiphop, drum and bass, chill)
lyricsNoProvide custom lyrics or leave blank for auto-generated ones.
durationNoMusic length in seconds, up to 240 (default: 240).
seedNoSet for reproducibility; -1 for random.

How to Use

  1. Enter style tags — add genres and moods like "lofi, hiphop, chill, trap."
  2. Add lyrics (optional) — provide custom lyrics or leave blank for AI-generated ones.
  3. Set duration — choose length from a few seconds up to 240 seconds (4 minutes).
  4. Set a seed (optional) for reproducible results.
  5. Click Run and wait for your music to generate.
  6. Preview and download the result.

Best Use Cases

  • Music Production & Songwriting — Generate complete demos or backing tracks instantly.
  • Film, Game & Media Scoring — Create mood-specific tracks with precise control.
  • Advertising & Content Creation — Design catchy audio for short-form content.
  • Education & Experimentation — Teach structure, genre, or lyric composition.
  • Soundtrack Prototyping — Preview musical direction before full studio production.

Pricing

DurationPrice
30 seconds$0.006
60 seconds$0.012
120 seconds$0.024
240 seconds$0.048

Billing Rules

  • Billed per second at $0.0002
  • Maximum duration: 240 seconds (4 minutes)

Pro Tips for Best Quality

  • Use multiple style tags to define genre, mood, and energy level.
  • Combine contrasting tags (e.g., "chill, trap") for unique blends.
  • Provide structured lyrics with line breaks for better vocal synchronization.
  • Start with shorter durations to test style combinations.
  • Fix the seed when iterating to compare different tag or lyric variations.

Notes

  • Processing time varies based on duration and current queue load.
  • Please ensure your content complies with usage guidelines.
Uwaga:Ta strona korzysta z modeli AI udostępnianych przez podmioty trzecie.

Ace Step API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/ace-step with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Ace Step below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "tags": "example",
    "duration": 60,
    "seed": -1
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/ace-step" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d "$REQUEST_BODY")

TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "$TASK" | jq -r '.urls.get // empty')
if [ -z "$RESULT_URL" ]; then
  RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
    -H "Authorization: Bearer $WAVESPEED_API_KEY")
  RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
  STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
  case "$STATUS" in
    completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
  esac
done
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/wavespeed-ai/ace-step";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');

async function requestJson(url, options = {}) {
  const response = await fetch(url, options);
  if (!response.ok) throw new Error(await response.text());
  return response.json();
}

// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "tags": "example",
        "duration": 60,
        "seed": -1
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;

// 2. Poll until the prediction finishes.
while (true) {
  const resultBody = await requestJson(resultUrl, {
    headers: { "Authorization": `Bearer ${apiKey}` },
  });
  const result = resultBody.data ?? resultBody;
  if (result.status === "completed") {
    console.log(result.outputs);
    break;
  }
  if (["failed", "cancelled", "timeout"].includes(result.status)) throw new Error(JSON.stringify(result));
  if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
  await new Promise(resolve => setTimeout(resolve, 2000));
}
Python example
import json
import os
import time
from urllib.request import Request, urlopen

api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
    "tags": "example",
    "duration": 60,
    "seed": -1
}

def request_json(url, data=None):
    request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
    with urlopen(request) as response:
        return json.load(response)

# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/wavespeed-ai/ace-step", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
    raise RuntimeError("Submission response did not contain a prediction id")
result_url = task.get("urls", {}).get("get") or f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"

# 2. Poll until the prediction finishes.
while True:
    result_body = request_json(result_url)
    result = result_body.get("data", result_body)
    status = result.get("status")
    if status == "completed":
        print(result.get("outputs", []))
        break
    if status in {"failed", "cancelled", "timeout"}:
        raise RuntimeError(result)
    if status not in {"created", "processing"}:
        raise RuntimeError(f"Unexpected status: {status}")
    time.sleep(2)

Ace Step API — Frequently asked questions

What is the Ace Step API?

Ace Step is a WaveSpeedAI model for audio generation, exposed as a REST API on WaveSpeedAI. ACE-Step generates up to 4-minute music with lyrics from text and high acoustic fidelity; supports voice cloning, lyric edits, and remixing. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Ace Step API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/wavespeed-ai/ace-step.

How much does Ace Step cost per run?

Ace Step starts at $0.000 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Ace Step accept?

Key inputs: `duration`, `seed`, `lyrics`, `tags`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/wavespeed-ai/ace-step.

How long does Ace Step take to generate?

Median end-to-end generation time on WaveSpeedAI is around 11 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.

Can I use Ace Step outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (WaveSpeedAI). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.

ACE Step | Realistic Voice & TTS API | WaveSpeedAI