gary4beatbox 4+

record w/mic. see where it go

Kevin Griffing

Designed for iPad

    • 4.7 • 3 Ratings
    • Free

Screenshots

Description

transform the audio with terry (aka melodyflow)

gary takes your input audio and runs away with it.

the first version was designed to continue your beatboxes. this new version has alot more use cases now that you can also transform with terry.

record using your mic, with or without noise cancellation, and with a count-in if you need it, and then send it to gary.

you can have it continue from where it left off, or you can crop off the end of its output and have it continue from there.

if you don't like the extended output, you can retry to have it go from the same place with different settings.

some features:

use any audiocraft/musicgen model on the huggingface hub by entering it into settings.

the 'tame the gary' setting is supposed to focus the output on percussion and drums, and hopefully retain more of your beatbox in its output. 
it's experimental and seems to only work well with the model 'thepatch/vanya_ai_dnb_0.1', but who knows...

the prompt duration is the number of seconds of audio you want it to use.
when you press 'send to gary' that number of seconds is counted from the beginning of the input.
when you press 'continue' or 'retry' that number is taken from the end of the audio.

share it as a video if you want to share to twitter, or un-toggle that to simply share the audio.

now in the app, we have 'terry'. it's the new model by meta, melodyflow. It can transform either your recorded audio or the audio you got back from gary.

undo what terry just did to try again. make sure to set the 'flowstep' which is kinda like the 'strength' of the transformation. it would seem higher is almost always better if you want it to truly retain the shape of what you gave to terry.

use presets or enter your own custom prompt to have terry transform the audio. this is very experimental. no other application in the world has this model in it.

learn more about terry here https://huggingface.co/spaces/facebook/Melodyflow

because this is free and open source, i'm really not sure how long our backend will stay up. 
you can change the backend url if you've built the backend from source:

https://github.com/betweentwomidnights/gary-backend-combined. (this uses the same backend as gary4live, the free ableton plugin that does whatever tf it wants)

What’s New

Version 2.0

now you can transform your input audio or the audio you get back from gary using terry.

Ratings and Reviews

4.7 out of 5
3 Ratings

3 Ratings

Ronzlo ,

Kid in a candy store…

First off - definitely beta version here. Crashes easily, such as when settings are changed. There’s a lag before it connects to the db, so when you hit ‘send to Gary’ give it a minute. Finally, only the Drum & Bass model seems to work well (as noted by devs.)

That said-

You can literally fart into the mic and it’ll crank out something usable for sampling purposes. I can’t stop messing around with it lol.

Developer Response ,

heard.

been furiously updating the app to fix issues with crashing. if it ever freezes while generating now, it should successfully go and grab your audio when you bring it back up.

then you can press 'restore' to keep bashing.

hoping most the problems you encountered have been solved now

appreciate you

kev
kev@thecollabagepatch.com




App Privacy

The developer, Kevin Griffing, indicated that the app’s privacy practices may include handling of data as described below. For more information, see the developer’s privacy policy.

Data Not Linked to You

The following data may be collected but it is not linked to your identity:

  • Identifiers
  • Usage Data

Privacy practices may vary, for example, based on the features you use or your age. Learn More

You Might Also Like

In Drones We Just
Music
Midi Amuser
Music
Grid Music Midi Player
Music
Sing Studio
Music
Fuzz Droid — Distortion Effect
Music
Harmonicc Chord Sequencer AUv3
Music