Sapienza NLP
Sapienza NLP
Audio model · Italy ·Oct 2025

FoleyGRAM

Audio Open Source

About FoleyGRAM

FoleyGRAM is an AI model developed by Sapienza NLP, in the audio category, released in 2025, made available as an open-source model. Video-to-audio (foley) generation model from Sapienza ISPAMM lab..

On this page you'll find FoleyGRAM's full specifications. Review provider pricing and benchmark scores below, or compare FoleyGRAM head-to-head with other audio models.

Links

Run FoleyGRAM locally

We don't have FoleyGRAM's size on file yet, so we can't say which GPUs fit it. As a rule of thumb a generative model needs a GPU whose VRAM comfortably exceeds the model's download size. Browse local-AI hardware →

Community

Would you run FoleyGRAM again?
No votes yet — be the first.
Did it run? — community reports by hardware

No reports yet. Own this model on some hardware? Be the first to confirm it runs.

Discussion

No comments yet. Start the discussion.

More models like FoleyGRAM

Frequently asked questions

What is FoleyGRAM?

Video-to-audio (foley) generation model from Sapienza ISPAMM lab. It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created FoleyGRAM?

FoleyGRAM was developed by Sapienza NLP and released in 2025.

Is FoleyGRAM open source or proprietary?

FoleyGRAM is released as open source — its weights are publicly available to download, run locally and fine-tune.

How much does FoleyGRAM cost?

Pricing for FoleyGRAM depends on the provider. See the providers table on this page for the latest API rates.

How does FoleyGRAM perform on benchmarks?

Benchmark scores for FoleyGRAM are listed on this page as they are published. You can compare it head-to-head with other models on the GenAIList compare tool.

No videos yet. Know a good one? Add it below.

Know a great video about FoleyGRAM?