Udio downloads are off: export-ready music for video work
Udio disabled downloads after its UMG settlement. Where to get an exportable AI music bed for video instead: Sume's Music Router returns a file URL.

Can you still download songs from Udio? Not as of the coverage I read on 2026-10-04. Reports say Udio disabled downloading on October 30, 2025, a day after its settlement with Universal Music Group, opened a short download window in early November, and is now building a licensed platform in which creations stay inside the service. If you need an audio file to put under a video, that is a dead end, and you want a generator that hands back a file.
Sume's Music Router does that: a finished job returns an audio artifact on media.sume.com, and you can use that URL in a render. This post compares the two flows without ranking the music itself, which I have no benchmark for.
What changed at Udio
The details here come from press coverage, not a Udio-owned page, so treat them as reported: the Rolling Stone feature covers the settlement and licensed-platform plan, and Music Business Worldwide covers the walled-garden debate. Check Udio's own terms for what you can do with anything made there.
The export difference, side by side
| Need | Udio, as reported | Sume Music Router |
|---|---|---|
| Get an audio file | Downloads disabled since Oct 30, 2025 | Audio artifact in result.artifacts[] |
| Use it in a video | Stays inside the platform | Pass the media.sume.com URL as soundtrack.url or audio.url |
| Pick the engine | Platform's own | sume/music-auto (Lyria 3.5 today) or lyria-3.5, lyria-3-pro |
| Cost per generation | Not checked | Fixed Music price per audio generation |
Fetch a file and read the URL
Poll the job envelope, then read the artifact where type is audio. The docs say to use Sume media URLs from the result because raw provider URLs are not public outputs.
curl https://api.sume.com/v1/jobs/job_123/result \
-H "Authorization: Bearer $SUME_API_KEY"Lay it under a video
Import the file or keep it on media.sume.com, then reference it as the soundtrack on a Timeline 1.0 render. The bed needs a real audio spine, not silence, if you also want it to duck under speech via duck_db.
Sources
Related posts
More in Comparisons
- Reading a vendor-run TTS leaderboard: Gemini 3.8 Flash TTS on VoiceEQ
Hume's blog lists Gemini 3.8 Flash TTS atop its Real-World VoiceEQ board. What that does and does not tell you, plus a blind test to run on your script.
- Veo 3.1 Lite at half of Fast vs an Omni Flash draft
Google says Veo 3.1 Lite costs under half of Veo 3.1 Fast. On Sume the Google video id is gemini-omni-flash-1.1, 3-10 s at 360p to 4K. Compare before budgeting.
- Reference limits: Veo 3.1, Gemini Omni Flash and Sume Video 1.0
Veo 3.1 takes up to 3 reference images, Omni Flash up to 3 clips of 3 s each, and Sume Video 1.0 takes 1 to 9 images. A table to pick by what you need to pin.
- Video API price per second: Veo, Runway, Luma, MiniMax, Seedance
A vendor-authored Higgsfield table lists Veo 3.1 at $0.40 per second down to MiniMax H3 at $0.08. What 10 seconds costs and why to verify each rate.
Written by Sume