Music

Mureka API

Songs planned like a musician, two takes per request.

Mureka generates full songs or instrumentals with custom or auto-generated lyrics, using chain-of-thought musical reasoning (MusiCoT) to plan structure before it renders a note.

Get API key Read the docs

2
Takes per request: ~90s
Avg. generation: 6 credits
Per request

Mureka Night Desk lo-fi instrumental, take A, After the Last Page

Playground

Try Mureka right here.

model: mureka

Prompt

Instrumental Generate instrumental tracks (no vocals). Not supported by mureka-o2.

Advanced settings

Lyrics Model version

Estimated cost 6 credits · $0.06 Generate in Studio

Output Example

Mureka Night Desk lo-fi instrumental, take B, After the Last Page — A melancholic lo-fi hip-hop track with vinyl crackle, a mellow piano loop, and soft jazz chords, instrumental, good for late-night studying.

Capabilities

What's new in Mureka.

Reasoning before rendering

Mureka plans the composition with MusiCoT, a chain-of-thought approach to musical structure, which shows in more coherent arrangements and transitions.

Songs or instrumentals

Full tracks with vocals, or pure instrumentals with a single flag. Bring your own lyrics or let the model write them from your prompt.

Two takes per call

Every request returns a pair of songs, the natural workflow for music, where variation between takes is the point.

Model version pinning

Pin a specific Mureka version for reproducible output in production, or track the latest as it improves.

Priced for iteration

6 credits (≈$0.06) for two tracks, cheap enough to generate several takes per brief and curate.

Same API as everything else

One POST request, async jobs, webhooks, and a unified credit balance shared with every image and video model on Apiframe.

Showcase

See what Mureka can create.

Real outputs generated with Mureka on Apiframe, each with the prompt behind it.

Try Mureka

Mureka vocal take A of Another Dawn, late-night study song — A melancholic lo-fi hip-hop track with vinyl crackle, a mellow piano loop, and a soft male vocal about late-night studying.

Mureka vocal take B of Another Dawn, late-night study song — A melancholic lo-fi hip-hop track with vinyl crackle, a mellow piano loop, and a soft male vocal about late-night studying.

Mureka Night Desk lo-fi instrumental, take A — A melancholic lo-fi hip-hop track with vinyl crackle, a mellow piano loop, and soft jazz chords, instrumental, good for late-night studying.

Pricing

Simple per-generation pricing.

6 credits per generation ≈ $0.06

You only pay for successful generations. Failed jobs are refunded automatically.
One credit balance across every model on Apiframe, no per-model plans.
Start with free credits. No subscription required.
Volume discounts on larger plans.

See plans and credit packs API pricing Mureka credit cost and rates

Specs

At a glance.

Provider Mureka

Model ID mureka

Audio Supported

Avg. time ~100s

Comparison

Mureka vs Producer AI vs Udio

Mureka against the fast option and the vocal specialist.

Feature	Mureka	Producer AI	Udio
Signature strength	MusiCoT structural reasoning	Speed + reproducible seeds	Vocal realism
Takes per request	Two songs	One song	One song
Avg. generation	~90s	~45s	~90s
Price per request	6 credits (≈$0.06)	6 credits flat (≈$0.06)	9–35 credits (≈$0.09–$0.35)
Best for	Coherent songs, two takes at once	Fast iteration with fixed seeds	Tracks where the vocal is the point

Specs reflect what each model supports on Apiframe today, from the live catalog.

Quickstart

How to call the Mureka API.

Send one POST /v2/music/generate request with your API key. The call returns a jobId you can poll, or pass a webhook_url and the result is pushed to you the moment it's ready.

Swap mureka for any other model and nothing else changes.

Get API key Read the docs

generate.js

const response = await fetch("https://api.apiframe.ai/v2/music/generate", {
  method: "POST",
  headers: {
    "X-API-Key": "afk_your_api_key_here",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "prompt": "an upbeat synthwave track with a driving bassline",
    "model": "mureka",
    "murekaParams": {
      "instrumental": false,
      "lyrics": "[Verse]…",
      "model_version": "auto"
    }
  }),
});
const { jobId } = await response.json();
console.log(jobId);

import requests

response = requests.post(
    "https://api.apiframe.ai/v2/music/generate",
    headers={
        "X-API-Key": "afk_your_api_key_here",
        "Content-Type": "application/json",
    },
    json={
        "prompt": "an upbeat synthwave track with a driving bassline",
        "model": "mureka",
        "murekaParams": {
            "instrumental": False,
            "lyrics": "[Verse]…",
            "model_version": "auto"
        }
    },
)
print(response.json())  # { "jobId": "...", "status": "QUEUED" }

curl -X POST https://api.apiframe.ai/v2/music/generate \
  -H "X-API-Key: afk_your_api_key_here" \
  -H "Content-Type: application/json" \
  -d '{
        "prompt": "an upbeat synthwave track with a driving bassline",
        "model": "mureka",
        "murekaParams": {
            "instrumental": false,
            "lyrics": "[Verse]…",
            "model_version": "auto"
        }
    }'

let job;
do {
  await new Promise((r) => setTimeout(r, 2000));
  job = await fetch("https://api.apiframe.ai/v2/jobs/JOB_ID", {
    headers: { "X-API-Key": "afk_your_api_key_here" },
  }).then((r) => r.json());
} while (job.status !== "COMPLETED" && job.status !== "FAILED");
console.log(job.result);

import requests, time

while True:
    job = requests.get(
        "https://api.apiframe.ai/v2/jobs/JOB_ID",
        headers={"X-API-Key": "afk_your_api_key_here"},
    ).json()
    if job["status"] in ("COMPLETED", "FAILED"):
        break
    time.sleep(2)
print(job["result"])

curl https://api.apiframe.ai/v2/jobs/JOB_ID \
  -H "X-API-Key: afk_your_api_key_here"

Input schema

Every field Mureka accepts, with types and defaults. The full reference lives in the docs.

Field	Type	Description
prompt required	string	Text description of what to generate.
model required	string	The model identifier for this endpoint. Default:"mureka" · "mureka"
murekaParams.instrumental	boolean	Generate instrumental tracks (no vocals). Not supported by mureka-o2. Default:false
murekaParams.lyrics	string	Optional — when left empty, lyrics are auto-generated from the prompt.
murekaParams.model_version	string	Model version Default:"auto" · "auto", "mureka-7.6", "mureka-o2", "mureka-8", "mureka-9"

Mureka versions

Every Mureka music model on Apiframe. Switch with one parameter.

Mureka Flagship This page

Use cases

What teams build with Mureka.

Generate takes, curate winners

Every request returns two takes, the natural music workflow, since variation between generations is where the keepers come from.

Structured arrangements

MusiCoT reasoning plans the composition before rendering, which shows in transitions and build-ups that feel arranged rather than looped.

Lyrics both ways

Bring exact lyrics and the vocals follow them, or hand the model a theme and let it write, one field switches the workflow.

Production pinning

Pin a model version so output stays stable in production, and upgrade on your schedule instead of the provider’s.

Reviews

9,800+ developers. One API.

Real Apiframe reviews from Trustpilot and G2.

Honestly the best AI API

They got every engine possible and it's great to have them all in one place.

Daniel Zborowski July 2026 Trustpilot

Excellent variety, low latency

The variety of models is excellent and the latency is low.

AG July 2026 Trustpilot

One simple API for powerful AI models

The best thing is that it gives access to many strong AI models in one simple API. Before, I had to rely on separate platforms for each task, but now I can handle everything through one API.

Anakin S. July 2026 G2

Mureka questions

What teams ask before shipping with Mureka. Everything else lives in the docs.

What is the Mureka API?

Programmatic access to Mureka, an AI music model that uses chain-of-thought reasoning (MusiCoT) to plan song structure. It generates full songs with vocals or instrumentals from a text prompt.

Can I provide my own lyrics?

Yes. Pass them in the lyrics field and the vocals follow them. Leave it empty and Mureka writes lyrics from your prompt, or set instrumental for no vocals at all.

How many songs do I get?

Every call returns two songs. You pick the keeper, the same pair-per-request shape as Suno and Udio.

How much does it cost?

6 credits (≈$0.06) per request, with typical completion around 90 seconds.

Where can you access it?

Through Apiframe with one API key, async jobs, and webhooks, no separate Mureka account needed.