AudioGen vs FoleyCrafter
AudioGen
github.comFoleyCrafter
foleycrafter.github.ioSide by side
| Figure | AudioGen | FoleyCrafter |
|---|---|---|
| Price from | Free | — |
| Free plan | Yes | — |
| Free trial | — | — |
| Open source | — | — |
| Web | — | Yes |
| Linux | Yes | — |
| API | Yes | — |
| Self-hosted | Yes | — |
| Plans published | 1 | 0 |
| Spec score · AI Sound Effect Generators | 8.8 (#2) | 7.3 (#23) |
| License | The repository says its code is MIT-licensed and its model weights use CC-BY-NC 4.0. | The repository lists an Apache-2.0 license and advises commercial users to check the Auffusion license as well. |
| Purpose | AudioGen is a text-to-sound generation model provided through AudioCraft. | FoleyCrafter is a text-based video-to-audio generation framework that produces high-quality audio semantically relevant and temporally synchronized with input video. |
| Support | The model card directs questions and comments to the project’s GitHub repository or its issue tracker. | The repository README lists contact email addresses for Yiming Zhang, YiCheng Gu, and Yanhong Zeng. |
| What it does | AudioGen is a text-guided audio generation model that generates sounds from text. | FoleyCrafter is a text-based video-to-audio generation framework that generates high-quality audio semantically relevant to and temporally synchronized with input videos. |
Plans
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.
FoleyCrafter
FoleyCrafter has no write-up on Specifiction yet; its figures are above.