Skip to content
SPECIFICTION
Get listed

AudioGen vs Noiz AI

AudioGen

github.com

Noiz AI

noiz.ai

Side by side

FigureAudioGenNoiz AI
Price fromFree—
Free planYes—
Free trial——
Open source——
Web—Yes
LinuxYes—
iOS—Yes
APIYes—
Self-hostedYes—
Plans published10
Spec score · AI Sound Effect Generators8.8 (#2)7.0 (#25)
Intended usersThe model card names audio, machine learning, and AI researchers, as well as amateurs learning about generative models, as primary users.The page names game and interactive creators, film and post-production teams, podcasters, YouTube creators, animators, and short-video creators as audiences.
PurposeAudioGen is a text-to-sound generation model provided through AudioCraft.Noiz AI generates Foley, ambience, UI sounds, and cinematic sound effects from text prompts or reference audio.
SupportThe model card directs questions and comments to the project’s GitHub repository or its issue tracker.Noiz lists [email protected], a contact and feedback option, and a Discord community.

Plans

AudioGen

  • AudioGen (self-hosted)Free

AudioGen pricing →

Noiz AI

No plans published.

Noiz AI pricing →

In their own words

AudioGen

AudioGen is a text-to-sound model provided through AudioCraft. It generates audio samples from text descriptions and can continue from an audio prompt, with conditional and unconditional generation modes. Sampling controls include greedy, temperature, top-K, and top-P methods. The listed pretrained model, facebook/audiogen-medium, has 1.5 billion parameters; the example API generates sound and saves it as WAV. The implementation uses an autoregressive Transformer and a 16 kHz EnCodec tokenizer. The repository provides API access and a local Jupyter notebook demo. Running the medium model locally requires a GPU with at least 16 GB of memory; installation requires Python 3.9 and PyTorch 2.1.0, with ffmpeg recommended. The model was trained on English descriptions and performs less well in other languages. It cannot generate realistic vocals, and prompts may need refinement. Code is MIT-licensed, while weights use CC-BY-NC 4.0; training datasets are not provided. The listed self-hosted plan is free.

Visit github.com

Noiz AI

Noiz AI has no write-up on Specifiction yet; its figures are above.

Visit noiz.ai