General feedback

The drop in sound quality is very noticeable. Or the quality of the song is now paywalled?

I'm consolidating all the 'bad output' posts together. This will be a lot easier for the devs to look into and potentially pick up more useful patterns of complaints and issues with the output. Reference note to everyone: The existing Udio models do not change in their output. They have not been worked upon or changed. I hope this is understood but I recognise that many users will still argue or say otherwise, this however can be demonstrated very clearly with seed output consistency, so we won't be getting into this debate or going down this rabbit hole with anyone as it's a waste of time* The things and issues that are brought up here are things that will be looked into and worked towards improving in future models, not the existing ones. Lets look towards the future and hopefully the output should always keep improving with the next upcoming model updates. Nothing is garaunteed though, for how much and in what way things will get improved or not. Given the nature of GenAI it can be rather difficult to completely predict or control things in a precise manner. *I say this but it is not 100% correct as there was a minor seed change on the 31st October. Which breaks full seed consistency to before that time but should not have affected the quality of output in any noticeable way and there should also still be some degree of seed consistency too. This is the only noticeable change that has been made to existing models though for a long time.

It's not a critical problem, but sometimes these words in lyrics are generated too often in any genres

I live this one "song" called "Text-to-speech Models Suck" showcasing the possibilitys of udios good text to speech model, I've tried to remake it for myself in German, translated the text, but wasted 400 coins, and got a bunch of nonsense, gibberish and a terrible voice, this is also for "music" what udios is intended for, I know. German "singers" almost always sounds robotic and like a Bored student.

PLEASE PLEASE PLEASE!, loosen the moderation checks, you cant moderate words thats not slurs, or foul language. The very least show what is preventing the track from being generated, so i can atleast try to modify the moderated element, of something that im sure is too strictly moderated already... stops me from wanting to punch my screen and chew a tree in half.

A feature to set the maximum volume level in dB would be useful. I have the impression that UDIO generates files that are clipped and sometimes distorted, especially in the high frequencies. The ability to input a parameter, for example, minus -(x) dB, would be very helpful.

Hello, how are you? I’d like to share some feedback about the $10 plan credits. Currently, the 1200 credits offered feel quite limited, especially since some audio generations fail, and the credits are still consumed. Increasing the credits to around 1800 or 2000 would make the plan much more attractive and fair. Additionally, here in Brazil, $10 is a relatively high amount due to the exchange rate, roughly equivalent to BRL 50. For us, it’s as if the plan costs $50 for someone in the U.S., which makes it less accessible for many Brazilian users. It’s also worth mentioning that Udio is widely used by professionals in Brazil, such as content creators and musicians. Since the platform is still in beta, increasing the credits or offering customizable plans could be a great strategy to outpace competitors and attract more users. Thank you for your attention, and I hope these suggestions help improve the platform!

With ambient or soundscapes, which should be as long as possible, these tracks become spongy and imprecise towards the end. That's a shame. Is there a trick to avoid this? Is it because of the prompt? I haven't noticed this with breakbeats. OK, I've now seen that this is a general problem when extending tracks. Too bad Udio, we could have been good friends. -

The app is getting better, even languages like Klingon (was an experiment) are supported and generate great songs... is there maybe a way that also the language of the Minions can be included... would be fun for my daughter. I use Udio a lot... it's more than a hobby... music is life for me... Thank you

Every UI update Udio has received in the past 4 months has made the interface less user friendly, especially for touchscreen devices, while introducing new bugs without fixing the existing ones. Future updates should be rolled out to users who opt-in to testing them to receive feedback before pushing them to production.