Udio API

High-quality music generation with custom lyrics.

Integrate Udio with a single API call — one key, one unified endpoint, and shared billing across every model on Apiframe.

Get API Key Use in Apiframe Studio View Udio API Docs

model: "udio"

What's special about Udio

Generates clips from 32s to 130s.
Generates natively synchronized audio.
Fast turnaround — about 90s per generation on average.
Pay-as-you-go pricing with no Udio account required — you only pay for successful generations.
One API key, unified billing, idempotency and webhooks across every Apiframe model.

Made with Udio

A few outputs generated through the Udio API on Apiframe.

Sample coming soon

Upbeat indie pop track with bright guitars and a catchy chorus

Sample coming soon

Lo-fi hip hop beat with mellow piano and soft vinyl crackle

Sample coming soon

Epic orchestral cinematic score with soaring strings and percussion

Overview

Endpoint: POST /v2/music/generate
Model ID: udio
Params key: udioParams
Modality: Music
Provider: Udio
Avg. completion: ~90s

Capabilities

Durations32s, 65s, 97s, 130s

AudioSupported

Avg. time~90s

Quick start

Send a single POST /v2/music/generate request with your API key to generate with Udio. The call returns a jobId you can poll or receive via webhook.

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": "udio",
        "udioParams": {
            "lyrics_type": "generate",
            "lyrics": "Optional — your own words",
            "lyrics_prompt": "e.g. leaving a small town at dawn",
            "title": "Optional"
        }
    }'

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": "udio",
        "udioParams": {
            "lyrics_type": "generate",
            "lyrics": "Optional — your own words",
            "lyrics_prompt": "e.g. leaving a small town at dawn",
            "title": "Optional"
        }
    },
)
print(response.json())  # { "jobId": "...", "status": "QUEUED" }

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": "udio",
    "udioParams": {
      "lyrics_type": "generate",
      "lyrics": "Optional — your own words",
      "lyrics_prompt": "e.g. leaving a small town at dawn",
      "title": "Optional"
    }
  }),
});
const { jobId } = await response.json();
console.log(jobId);

Response & job lifecycle

Generation is asynchronous. A successful submission returns 202 Accepted with a jobId. Poll GET /v2/jobs/{id} (or supply a webhook_url) until the status is COMPLETED; the result field then holds the output URL(s).

1. Submission response (202)

{
  "jobId": "b2c3d4e5-f6a7-8901-bcde-f23456789012",
  "status": "QUEUED"
}

2. Poll for the result

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

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"])

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);

Input schema

Request parameters accepted by the Udio endpoint. Model-specific options are nested under the params object shown below.

Parameter	Type	Required	Default	Allowed / range	Description
prompt	string	required	—	—	Text description of what to generate.
model	string	required	"udio"	"udio"	The model identifier for this endpoint.
udioParams.lyrics_type	string	optional	"generate"	"generate", "user", "instrumental"	Lyrics
udioParams.lyrics	string	optional	—	—	Your lyrics
udioParams.lyrics_prompt	string	optional	—	—	Udio writes the lyrics from this, free, before the song is generated.
udioParams.title	string	optional	—	—	Track title
udioParams.style	string	optional	—	—	Style hints
udioParams.negative_tags	string	optional	—	—	Negative tags
udioParams.model	string	optional	"udio32-v1.5"	"udio32-v1.5", "udio32-v1", "udio32-v2", "udio130-v1.5", "udio130-v1"	The udio130 models cannot be extended afterwards.
udioParams.bpm	number	optional	—	min 60, max 200, step 1	BPM
udioParams.prompt_strength	number	optional	—	min 0, max 1, step 0.05	Prompt strength
udioParams.lyrics_strength	number	optional	—	min 0, max 1, step 0.05	Lyrics strength
udioParams.clarity_strength	number	optional	—	min 0, max 1, step 0.05	Clarity
udioParams.generation_quality	number	optional	—	min 0, max 1, step 0.05	Generation quality
udioParams.manual_mode	boolean	optional	false	—	Send the prompt verbatim, without Udio’s prompt optimizer.
udioParams.style_ref	string	optional	—	—	Udio’s "Use a Style" tab. Setting this generates from the style instead of a description, so the prompt becomes optional.
udioParams.voice	string	optional	—	—	A voice to sing it.
udioParams.seed	number	optional	—	step 1	Reuse a number to reproduce the same result.

Frequently Asked Questions

Common questions about the Udio API.

Is there an API for Udio?

Yes. Apiframe exposes Udio through a single REST endpoint (`POST /v2/music/generate` with `model: "udio"`). You get one unified API, key, and billing across every supported model — no separate Udio account required.

How much does the Udio API cost?

Udio uses simple pay-as-you-go pricing on Apiframe — you only pay for successful generations. See the pricing page for plans and volume discounts.

How do I call the Udio API?

Send a POST request to `/v2/music/generate` with your `X-API-Key` and a JSON body containing `model: "udio"`. The call returns a `jobId`; poll `GET /v2/jobs/{id}` or use a webhook to receive the result.

What parameters does Udio support?

Udio accepts 16 model-specific parameters (nested under `udioParams`) plus the common `prompt` and `webhook_url` fields. See the input schema above for the full list with types and defaults.

Still have questions?

Contact Support Join Discord

Start building with the Udio API

Get your API key and integrate Udio in minutes — Pay-as-you-go.

Free credits to start

One API for every model

Webhooks, SDKs & idempotency

No provider account required

Get Started Free Read Documentation

Questions? Join our Discord or contact sales.

Udio API

What's special about Udio

Made with Udio

Overview

Capabilities

Quick start

Response & job lifecycle

1. Submission response (202)

2. Poll for the result

Input schema

Related models

Frequently Asked Questions

Start building with the Udio API