AudioGen vs Sonilo
AudioGen
github.comSonilo
sonilo.comSide by side
| Figure | AudioGen | Sonilo |
|---|---|---|
| Price from | Free | $11.99/mo |
| Free plan | Yes | Yes |
| Free trial | — | Yes |
| Open source | — | — |
| Web | — | Yes |
| Linux | Yes | — |
| iOS | — | Yes |
| Android | — | Yes |
| API | Yes | Yes |
| Self-hosted | Yes | — |
| Plans published | 1 | 4 |
| Spec score · AI Sound Effect Generators | 8.8 (#2) | 7.8 (#13) |
| Support | The model card directs questions and comments to the project’s GitHub repository or its issue tracker. | General support is provided at [email protected], privacy requests at [email protected], and enterprise inquiries through sales. |
| Training data | The instructions say the datasets used to train AudioGen are not provided. | Sonilo says its models use licensed music datasets, including content authorized through Shutterstock. |
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.
Sonilo
Sonilo generates music and sound effects intended to follow a video's pacing, mood and scene changes. Users can upload MP4 or MOV video, or describe the desired audio in text. Sonilo processes the visuals while leaving the original audio available to keep, adjust, replace or layer. It generates several variations by default and accepts an optional prompt to guide style. The service also supports speech translation, video re-voicing, lip-sync re-rendering and SRT or VTT subtitles. Its API covers music and sound-effects generation, audio ducking, task polling and account usage; plugins are listed for Adobe Premiere Pro, Unity, Godot, Epic Games Fab, Roblox Studio and Defold. Free provides 2,000 credits every two weeks, with preview-quality exports and videos up to 3 minutes. Pro is $11.99 a month, billed yearly as $143.88, and Premium is $23.99 a month, billed yearly as $287.88. Commercial use is limited to specified paid plans and eligible API users. Sonilo says uploaded videos, prompts, outputs and related data may be used for training and product improvement by default.