Suggestions appear as you type. Use the up and down arrows to choose one and Enter to open it.

This page's audience our own tag's counts — open to see them
–Visits
–Page views
–Clicks to vendors
–Time on page
–Reading now
Clicks to vendors, by tool
  • –
Top countries
  • –
Devices
  • –

– · visits, page views and clicks counted by our own tag, which counts more than our checked analytics; every figure rounded down · how we count

AudioGen review

A configurable local model for researchers, with restricted commercial use and no hosted app.

7.1/10Editor score
AudioGen7.1 Explore AudioGen

Reviewed by iTechGuides Editors · Editorial team · Updated Oct 2026

AudioGen is an open-source text-to-sound generation model from Meta AI’s FAIR team. It is designed for audio, machine-learning and AI researchers, along with amateurs exploring generative audio. The model generates general environmental audio from natural-language descriptions using an autoregressive Transformer and 16 kHz EnCodec-based audio tokenization. Its released medium model has 1.5 billion parameters and runs locally through the AudioCraft Python library, making it a fit for custom workflows rather than a hosted commercial sound-effects application.

For research and development, AudioGen provides more than prompt-based generation. The feature set includes audio continuation from an audio prompt, configurable generation duration and sampling parameters, and a Python inference API through AudioCraft. Training and evaluation pipelines support custom research workflows, while the model’s open-source distribution allows local work with the released system. These capabilities make AudioGen particularly relevant when researchers need to inspect, adapt or integrate generation into their own Python-based processes.

The main trade-off is the product’s local, research-focused delivery model. AudioGen is distributed as a model and local research library rather than a hosted commercial application, so it is less convenient for creators seeking a ready-to-use browser workflow. The model weights use the CC-BY-NC 4.0 license, restricting commercial use. Researchers building custom local audio systems should consider AudioGen; creators needing straightforward commercial production workflows or a hosted experience should choose a tool aligned with those requirements instead.

AudioGen pros and cons

  • Where it wins
    • Generates environmental audio from natural-language descriptions
    • Includes Python inference, continuation, and configurable sampling
    • Provides training and evaluation pipelines for custom research workflows
  • Where it doesn't
    • Requires self-hosting through a local research library
    • Commercial use is restricted by the CC-BY-NC 4.0 license
    • Research-oriented tooling may be less convenient for typical creators

AudioGen fact sheet, pricing and score →

Advertiser disclosure: iTechGuides is reader-supported. Vendors can pay for top positions in our rankings and for a place on other products' pages, and we may earn a commission when you click some links. Bought places stand at the number bought; this page and our disclosure say so. Paying vendors may get a fuller, more detailed review from our editors, and that review can change their score. How we rank.

Last updated · How we research and update