Music

Udio API

The most natural vocals in AI music, with every dial exposed.

Udio generates full songs with some of the most natural-sounding vocals in AI music, across any genre. On Apiframe you get the complete control surface, lyrics, style, BPM, voice, and reproducible seeds, through one API.

Get API key Read the docs

130s
Max duration: 16+
API controls: ~90s
Avg. generation: 9 credits
From

Udio retro-soul track It’s Only Love, ruby-lit club cover

Playground

Try Udio right here.

model: udio

Prompt

Duration

Lyrics

Advanced settings

Your lyrics What the lyrics are about Track title Style hints Negative tags Model version BPM Prompt strength Lyrics strength Clarity Generation quality Manual mode Send the prompt verbatim, without Udio’s prompt optimizer. Generate from a style Voice Seed

Estimated cost 1–35 credits · $0.01–$0.35 Generate in Studio

Output Example

Udio pop-soul anthem Break Away Tonight — An upbeat retro-soul track with a powerful female lead vocal, horn stabs, and a driving bassline, sounds like it was cut live in a 70s studio.

Capabilities

What's new in Udio.

Vocals that sound human

Udio's signature is vocal realism, phrasing, breath, and delivery that hold up outside a demo. The Allegro engine handles any genre, from country to hyperpop.

Your lyrics or generated ones

Write the exact lyrics, give a lyric brief and let the model write them, or go instrumental, the lyrics_type switch covers all three workflows.

Four track lengths

Generate 32, 65, 97, or 130-second tracks. Short clips for social, full arrangements for everything else, priced from 9 credits at the short end.

Producer-level dials

BPM, style tags, negative tags, prompt/lyrics/clarity strength, generation quality, and manual mode expose the full Udio control surface through the API.

Style and voice references

Point at a style reference or a voice to steer the sound of the track, consistency across a series of generations instead of a new sound every roll.

Reproducible with seeds

Fix the seed to reproduce a take, then vary one parameter at a time, the workflow serious teams use to iterate toward a final track.

Showcase

See what Udio can create.

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

Try Udio

Udio neo-soul ballad Stay Till the Last Song with custom lyrics — A vocal-led neo-soul ballad, intimate female lead, brushed drums, warm Rhodes, late-night club. Lyrics: Ruby Room, lights down low. Horns talk back, let the night unfold. Ruby Room, don’t you go. Stay till the last song, that’s how we know.

Udio 32-second jazz-club instrumental Last Call — Short instrumental jazz-club bed, muted trumpet, walking bass, brushed snare, smoky and unhurried, no vocals.

Udio 70s retro-soul track It’s Only Love — An upbeat retro-soul track with a powerful female lead vocal, horn stabs, and a driving bassline, sounds like it was cut live in a 70s studio.

Pricing

Simple per-generation pricing.

1–35 credits per generation ≈ $0.01–$0.35

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 API pricing Udio credit cost and rates

Specs

At a glance.

Provider Udio

Model ID udio

Durations 32s, 65s, 97s, 130s

Audio Supported

Avg. time ~135s

Comparison

Udio vs Lyria 3 Pro vs Mureka

Udio against the other full-song generators on Apiframe.

Feature	Udio	Lyria 3 Pro	Mureka
Max length	130 seconds	~3 minutes	Full songs
Signature strength	Vocal realism + 16-control surface	Structure + image-to-music	MusiCoT structural reasoning
Custom lyrics	Verbatim, with strength dial	Time-aligned placement	Verbatim or auto-generated
Price per track	9–35 credits (≈$0.09–$0.35)	10 credits flat (≈$0.10)	6 credits (≈$0.06)
Best for	Vocal-led tracks and fine control	Finished songs and scored scenes	Batch takes and coherent arrangements

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

Quickstart

How to call the Udio 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 udio 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": "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);

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" }

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"
        }
    }'

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

Udio versions

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

Udio Flagship This page

Use cases

What teams build with Udio.

Vocal-led tracks

When the song needs to carry a voice, jingles, theme songs, artist-style demos, Udio's vocal realism is the reason to pick it.

Exact-lyrics workflows

Pass lyrics verbatim and they get sung as written, with a strength dial for how strictly. Brand names and taglines land intact.

Consistent series

Style references, voice selection, and seeds keep a series of tracks sounding like one artist instead of a different band per generation.

Cheap short-form

The 32-second tier starts at 1 credit (≈$0.01), background tracks for social content at a cost that rounds to zero.

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

Udio questions

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

What is the Udio API?

Programmatic access to Udio, the AI music model known for realistic vocals and strong genre range. Apiframe exposes it through the same unified API as every other music model.

How long can tracks be?

Four durations: 32, 65, 97, or 130 seconds. Pricing scales with length, starting at 9 credits (≈$0.09) for the shortest tier up to 35 credits (≈$0.35) for the longest.

Can I provide my own lyrics?

Yes. Set lyrics_type to custom and pass your lyrics verbatim, use a lyric prompt to have them written for you, or generate a pure instrumental.

What controls are available?

Title, style and negative tags, BPM, voice and style references, prompt/lyrics/clarity strength, generation quality, manual mode, and seed, the full Udio surface.

How long does generation take?

Around 90 seconds for a typical track. Jobs are async: poll the jobId or pass a webhook_url and the result is pushed when ready.