Music and sound

Udio v1.5 (Allegro)

Name: Udio v1.5 (Allegro)
Author: Udio

Generates songs with vocals from a text prompt and optional user lyrics, in 32-second or 130-second segments that can be extended, remixed, inpainted and arranged on a Sessions timeline. v1.5 Allegro (18 March 2025) is the current documented model, adding faster generation.

An audio model by Udio · read 2026-08-14 · sourcing medium

Up to: 130 seconds
Weights: Not released
API: No
Commercial use: Rights are not withheld, but output cannot be exported

Since 30 October 2025 audio downloads have been disabled following the Universal Music settlement, so output is create-and-stream only inside Udio.

Commercial use — Rights are not withheld, but output cannot be exported

Udio does not claim ownership of what you generate. The obstacle is export: downloads were disabled on 30 October 2025 after the UMG settlement, and the replacement product is described as a walled garden in which generated music cannot be exported or posted elsewhere. Treat it as unusable for video delivery until export returns.

Attribution required. Free-account users must indicate that the content was generated using Udio.

This entry was written by hand from the licence wording quoted above, because the source dataset's yes/no field was misleading here. Read the licence before you rely on any of this. Nothing on this page is legal advice, and this site does not tell you a model is cleared for commercial use.

Specification

Vendor figures, read 2026-08-14Read from Udio's own documentation on 2026-08-14. Vendors change these between model versions without announcing it, so check theirs before you commit a shot to a number. Sourcing for this entry is mixed. Some fields came from pages we retrieved, others could not be confirmed and are left blank. Check the vendor's current documentation

What it takes in: text, lyrics, audio
What it makes: audio
Maximum duration: 130 seconds
Controls: lyrics-input, style-prompting, instrumental-only, extend, inpainting-remix, reference-audio, tempo-key-control
Weights: Not released
API: No
Pricing: Credit subscription. Free: 10 credits/day with a 100 credits/month cap and a hard limit of three 130-second songs per day. Standard: up to 2,400 credits/month. Pro: up to 6,000 credits/month, up to 10 simultaneous generations. Each Create/Extend/Remix/Inpaint/Edit action produces two songs; a pair of 32-second songs costs 2 credits and a pair of 130-second songs costs 4 credits. Credits do not roll over; separately purchased credits never expire. Dollar prices are not published on a vendor page that could be fetched.
Released or updated: 2025-03-18

Strengths

Strong prompt-driven vocal music quality
Sessions timeline editing, inpainting and remix
Explicit no-ownership-claim language from the vendor
Clear per-generation credit accounting

Weaknesses

Audio downloads disabled since 30 October 2025 with no announced restoration date - you cannot get a file out
Announced move to a closed walled garden where output may not leave the platform at all
Short 130-second base generations require extension
Changelog last updated 28 January 2026; model version has not advanced past v1.5 Allegro
No API
Sony Music litigation reported as ongoing

Best for

Experimentation and listening only, until export is restored

Where the sources disagree

Recorded rather than resolved. Picking the tidier number would hide the fact that the vendor's own pages do not agree.

Udio's help centre still describes commercial use and attribution as if downloads work, and third-party writeups say Standard/Pro grant 'non-exclusive, perpetual, worldwide' commercial licences; this conflicts with the fact that downloads have been disabled since 30 October 2025. The udio.com/terms-of-service page is JavaScript-rendered and could not be fetched to confirm the current licence text.
Vendor dollar prices ($10 Standard / $30 Pro are widely reported by third parties) could not be confirmed on a Udio-owned page, so they are excluded.
The exact date downloads were disabled is reported as 30 October 2025 by third parties; Udio's changelog does not record it.

What to understand before using it

Explainers naming the mechanisms this model's own documentation mentions.

Camera control: a move without a camera names “control”
Conditioning and control: everything you hand the model besides noise names “control”
Open weights versus closed API: renting or owning the model names “closed”

MCP servers that front Udio

Servers in the media MCP directory whose own description or homepage names this vendor. Absence of a server here is not evidence that none exists: most publish no tool list at all.

THIRI Chord Intelligence Music
Deterministic music theory for agents: analyze, voice, reharmonize, conduct, computed, not guessed.

See it from the vendor

Shotcraft hosts no sample output. Judging a model means watching its own showreel with your own eyes, and a clip re-hosted here would be a clip we chose.

Nearby in the directory

ACE-Step

An open-source music generation foundation model combining diffusion with a lightweight linear transformer, released May 2025 by ACE Studio and StepFu

Music and sound

AIVA

Generates instrumental music from style presets and influence uploads for video, game and content creators, exporting MP3 and MIDI on lower tiers and

Music and sound

Beatoven.ai maestro

Generates royalty-free background music and text-prompted sound effects for video, podcast, game and advertising work, downloadable as MP3 or WAV with

Music and sound

Sources

Read on 2026-08-14. A source that has changed since then will not be reflected here until the next pass.