Seedance 2.5 đã ra mắt | Dùng thử trong trình tạo video →

mureka-ai/

Mureka AI O2 Generate Song is a fast AI music generation model that creates high-quality songs via the official Mureka API. Ready-to-use REST inference API for AI song generation, lyrics-to-music workflows, vocal music creation, demo production, creative audio projects, and professional music generation with simple integration, no coldstarts, and affordable pricing.

text-to-audio
Đầu vào

Chờ

$0.05cho mỗi lần chạy·~20 / $1

Ví dụXem tất cả

Mô hình liên quan

README

Mureka AI O2 Generate Song

Mureka AI O2 Generate Song creates full songs from lyrics with optional style prompting and optional reference inputs for melody, vocals, or overall musical direction. It is suitable for songwriting, demo generation, vocal-guided creation, and fast music prototyping workflows.

Why Choose This?

  • Lyrics-to-song generation Turn written lyrics into complete song outputs with minimal setup.

  • Optional style prompting Add a prompt to guide genre, mood, instrumentation, arrangement, or production style.

  • Reference-based control Use optional reference_id, vocal_id, or melody_id inputs to steer the result more precisely.

  • Multiple generations per run Generate up to 3 songs in a single request with number_of_songs.

  • Flexible output formats Export generated songs as mp3, wav, or flac.

  • Simple pricing Pricing depends only on how many songs you generate.

Parameters

ParameterRequiredDescription
lyricsYesLyrics for the generated song. Official limit: up to 3000 characters.
promptNoOptional style prompt for the song. Official limit: up to 1024 characters.
number_of_songsNoNumber of generations. Range: 1–3. Default: 1.
output_formatNoOutput audio format after re-uploading to WaveSpeed CDN. Supported values: mp3, wav, flac. Default: mp3.
reference_idNoOptional Mureka uploaded reference file ID.
vocal_idNoOptional Mureka uploaded vocal file ID.
melody_idNoOptional Mureka uploaded melody file ID.

How to Use

  1. Write your lyrics — provide the lyrics you want to turn into a song.
  2. Add a style prompt (optional) — describe genre, mood, instrumentation, tempo, or production feel.
  3. Add references (optional) — use reference_id, vocal_id, or melody_id if you want more control over the result.
  4. Set number of songs — choose how many generations you want, from 1 to 3.
  5. Choose output format — select mp3, wav, or flac.
  6. Submit — run the model and download the generated songs.

Example Prompt

Emotional pop ballad with piano, warm strings, cinematic chorus, expressive female vocal, polished modern production

Pricing

Pricing is based on number_of_songs.

Number of SongsCost
1$0.05
2$0.10
3$0.15

Billing Rules

  • Each generated song costs $0.05
  • Total price = $0.05 × number_of_songs
  • prompt, output_format, reference_id, vocal_id, and melody_id do not affect pricing

Best Use Cases

  • Songwriting demos — Quickly turn lyrics into draft songs for evaluation and iteration.
  • Style exploration — Test the same lyrics across different genres, moods, and arrangements.
  • Reference-guided generation — Use melody or vocal references to guide the resulting song.
  • Content creation — Generate original song material for videos, social content, and creative projects.
  • Music ideation — Explore multiple song directions in a single run with number_of_songs.

Pro Tips

  • Keep lyrics clearly structured with verses, choruses, and bridges when possible.
  • Use the style prompt to specify genre, instrumentation, vocal tone, tempo, and production feel.
  • Increase number_of_songs when you want multiple variations from the same lyrics.
  • Use reference_id, vocal_id, or melody_id only when you want tighter guidance over the output.
  • Start with mp3 for convenience, then use wav or flac when higher-quality output matters more.

Notes

  • lyrics is required.
  • number_of_songs supports values from 1 to 3.
  • lyrics supports up to 3000 characters.
  • prompt supports up to 1024 characters.
  • output_format defaults to mp3.
  • Pricing depends only on number_of_songs.

Related Models

Lưu ý:Trang web này sử dụng các mô hình AI do bên thứ ba cung cấp. Giá trong tài liệu chỉ để tham khảo và có thể đã lỗi thời. Nút Generate hiển thị giá ước tính; phí cuối cùng của tác vụ sẽ được áp dụng.

Mureka O2 Generate Song API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/mureka-ai/mureka-o2/generate-song 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 Mureka O2 Generate Song below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "lyrics": "example",
    "number_of_songs": 1,
    "output_format": "mp3"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/mureka-ai/mureka-o2/generate-song" \
  -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/mureka-ai/mureka-o2/generate-song";
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 ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "lyrics": "example",
        "number_of_songs": 1,
        "output_format": "mp3"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${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 = {
    "lyrics": "example",
    "number_of_songs": 1,
    "output_format": "mp3"
}

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/mureka-ai/mureka-o2/generate-song", 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)

Mureka O2 Generate Song API — Frequently asked questions

What is the Mureka O2 Generate Song API?

Mureka O2 Generate Song is a Mureka Ai model for audio generation, exposed as a REST API on WaveSpeedAI. Mureka AI O2 Generate Song is a fast AI music generation model that creates high-quality songs via the official Mureka API. Ready-to-use REST inference API for AI song generation, lyrics-to-music workflows, vocal music creation, demo production, creative audio projects, and professional music generation with simple integration, no coldstarts, and affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Mureka O2 Generate Song 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/mureka-ai/mureka-ai-mureka-o2-generate-song.

How much does Mureka O2 Generate Song cost per run?

Mureka O2 Generate Song starts at $0.050 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 Mureka O2 Generate Song accept?

Key inputs: `prompt`, `lyrics`, `melody_id`, `number_of_songs`, `output_format`, `reference_id`. 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/mureka-ai/mureka-ai-mureka-o2-generate-song.

How long does Mureka O2 Generate Song take to generate?

Median end-to-end generation time on WaveSpeedAI is around 55 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 Mureka O2 Generate Song outputs commercially?

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