#ai #music #audiocraft

* audio quality of output is low.
* results from text input rarely match intent.
* tried creating drum breaks / loops with audio-gen, but again, odd results (maybe I should experiment more with music-gen for syncopated samples?)
* HOWEVER, it generates some truly odd / unique audio.
* requesting vocals and chords, came up with some very intriguing "melodic noises.'
* would like to explore 'training' further and curious if any way to up the output quality? (upscale?)

NEW! AwesomeCast 651: Big Sonic Bada Boom in the Blue Sky

w/ @profpod @Chilla @sorgatron

Audio: https://www.patreon.com/posts/87408962
Video: https://www.patreon.com/posts/87408981

#supersonictravel #Xplane #NASA #quietsupersonicjet #iOS17 #CarPlay #AudioCraft #AI #Beeper #messaging #GM #EVs #PremierePro #transcriptfeature #AIadoption

I just did a local installation of audio-webui and wanted to see how #AudioCraft generates music with #musicgen models.

This is my "first" #AI generated music clip with #AudioCraft models, only small snippet and so much more to explore.

https://github.com/gitmylo/audio-webui

if you are trying to get #audiocraft from #meta working on a M1/M2 mac, these two helpers were necessary for me:

https://medium.com/@alfredolhuissier/how-to-install-audiocraft-meta-ai-music-generation-ai-locally-on-mac-and-windows-too-f340ceb75ada

https://github.com/facebookresearch/audiocraft/files/11772278/xformers_patch.txt

#python

#Music #AI #GenerativeAI #AudioCraft #Meta #OpenSource: "On Wednesday, Meta announced it is open-sourcing AudioCraft, a suite of generative AI tools for creating music and audio from text prompts. With the tools, content creators can input simple text descriptions to generate complex audio landscapes, compose melodies, or even simulate entire virtual orchestras.

AudioCraft consists of three core components: AudioGen, a tool for generating various audio effects and soundscapes; MusicGen, which can create musical compositions and melodies from descriptions; and EnCodec, a neural network-based audio compression codec.

In particular, Meta says that EnCodec, which we first covered in November, has recently been improved and allows for "higher quality music generation with fewer artifacts." Also, AudioGen can create audio sound effects like a dog barking, a car horn honking, or footsteps on a wooden floor. And MusicGen can whip up songs of various genres from scratch, based on descriptions like "Pop dance track with catchy melodies, tropical percussions, and upbeat rhythms, perfect for the beach."

Meta has provided several audio samples on its website for evaluation. The results seem in line with their state-of-the-art labeling, but arguably they aren't quite high quality enough to replace professionally produced commercial audio effects or music."

https://arstechnica.com/information-technology/2023/08/open-source-audiocraft-can-make-dogs-bark-and-symphonies-soar-from-text-using-ai/

🧠 Meta AI presenta #AudioCraft, una nuova famiglia di modelli di #AI generativa in grado di produrre audio e musica realistici e di alta qualità da un #prompt testuale.
🔗 Il progetto: https://audiocraft.metademolab.com/
🔗Alcuni sample: https://audiocraft.metademolab.com/musicgen.html

#IntelligenzaArtificiale #TextToAudio #LLM #GenerativeAI