Music

ElevenLabs Music API

Long-form music, cut to the exact millisecond.

ElevenLabs Music brings the audio quality ElevenLabs is known for to long-form composition, tracks up to five minutes in a single generation, with millisecond-precise length control.

Get API key Read the docs

5 min
Max length: 1ms
Length precision: ~60s
Avg. generation: 9 credits
From

elevenlabs-music

Music model

A cinematic orchestral piece that builds from a solo piano to full strings and percussion over three minutes, hopeful, epic finale.

Playground

Try ElevenLabs Music right here.

model: elevenlabs-music

Prompt

Track length (ms)

Instrumental

Advanced settings

Output format

Estimated cost 9–94 credits · $0.09–$0.94 Generate in Studio

Output

Your output lands here. Hit generate to run this request in Studio.

Capabilities

What's new in ElevenLabs Music.

Up to 5 minutes in one pass

The longest single-generation tracks on Apiframe. Podcasts intros, full background beds, and complete songs without stitching segments together.

Millisecond length control

Set music_length_ms and the track lands at exactly that length, critical when the music has to fit a fixed video edit or ad slot.

ElevenLabs audio DNA

Built by the team behind the leading voice AI, with the same attention to fidelity and vocal realism applied to full musical arrangements.

Instrumental when you need it

A force_instrumental flag guarantees no vocals, the safe setting for background music under narration or dialogue.

Format control

Pick the output format that fits your pipeline instead of transcoding after the fact.

Length-based pricing

From 9 credits (≈$0.09) for short tracks up to 94 (≈$0.94) for a full five minutes, you pay for the seconds you request.

Pricing

Simple per-generation pricing.

9–94 credits per generation ≈ $0.09–$0.94

The rate depends on the resolution and options you pick.

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 Provider prices Compare ElevenLabs Music pricing vs fal.ai and others

Specs

At a glance.

Provider ElevenLabs

Model ID elevenlabs-music

Audio Supported

Avg. time ~25s

Comparison

ElevenLabs Music vs Lyria 3 Pro vs Udio

ElevenLabs Music against the other premium song generators.

Feature	ElevenLabs Music	Lyria 3 Pro	Udio
Max length	5 minutes	~3 minutes	130 seconds
Length control	Exact, in milliseconds	Via prompt and structure	Four fixed durations
Avg. generation	~60s	~90s	~90s
Price per track	9–94 credits (≈$0.09–$0.94)	10 credits flat (≈$0.10)	9–35 credits (≈$0.09–$0.35)
Best for	Exact-length and long-form audio	Finished songs and scored scenes	Vocal-led tracks and fine control

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

Quickstart

How to call the ElevenLabs Music 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 elevenlabs-music 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": "elevenlabs-music",
    "elevenlabsParams": {
      "music_length_ms": 60000,
      "force_instrumental": false,
      "output_format": "mp3_high_quality"
    }
  }),
});
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": "elevenlabs-music",
        "elevenlabsParams": {
            "music_length_ms": 60000,
            "force_instrumental": False,
            "output_format": "mp3_high_quality"
        }
    },
)
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": "elevenlabs-music",
        "elevenlabsParams": {
            "music_length_ms": 60000,
            "force_instrumental": false,
            "output_format": "mp3_high_quality"
        }
    }'

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 ElevenLabs Music 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:"elevenlabs-music" · "elevenlabs-music"
elevenlabsParams.music_length_ms	number	5,000 ms = 5 seconds · 300,000 ms = 5 minutes. Default:60000 · min 5000, max 300000, step 1000
elevenlabsParams.force_instrumental	boolean	Instrumental Default:false
elevenlabsParams.output_format	string	Output format Default:"mp3_high_quality" · "mp3_standard", "mp3_high_quality", "wav_16khz", "wav_22khz", "wav_24khz", "wav_cd_quality"

ElevenLabs versions

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

ElevenLabs Music Flagship This page

Use cases

What teams build with ElevenLabs Music.

Music cut to picture

Set music_length_ms to the exact length of the edit and the track lands on it, no fading out a loop or trimming a longer take.

Beds under narration

force_instrumental guarantees vocal-free tracks for podcasts, explainers, and ads where music sits under speech.

Long-form without stitching

Up to five minutes in one generation, full background beds and complete songs with a coherent arc, not segments glued together.

In-app soundtracks

Length-priced from 9 credits, it slots into products that need on-demand music at predictable, duration-based cost.

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

ElevenLabs Music questions

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

What is the ElevenLabs Music API?

Programmatic access to ElevenLabs' music generation model, which composes long-form tracks, up to five minutes, with the audio fidelity the company is known for from voice AI.

How long can tracks be?

Up to 5 minutes in a single generation, set precisely in milliseconds with music_length_ms. Pricing scales with the requested length, from 9 to 94 credits.

Can it make instrumental-only tracks?

Yes. Set force_instrumental to guarantee a track with no vocals, ideal for background beds under speech.

What is it best for?

Anything that needs exact-length or long-form audio: video soundtracks cut to a fixed edit, podcast beds, in-app background music, and full songs.

How long does generation take?

Around a minute for typical requests. Jobs are async, poll the jobId or receive the finished track on a webhook.