AudioGen vs Sonicker

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.

Sonicker is a web service that creates sound effects from written prompts. You can request foley, ambience, impacts, user-interface sounds, scene audio, reactions, alerts, devices, weather, money sounds, cinematic effects, or trending sounds. Its workbench supports both isolated hits and fuller environmental audio, and the page says results can be generated in seconds. The browser interface uses a text prompt and Generate control. Downloads are described as commercial-ready for editing, mockups, social content, and production workflows. Each sound-effects generation is shown as costing 40 credits. A free plan provides 55 credits monthly plus 10 at signup; paid plans start at $9.90 a month when billed annually. Unused subscription credits expire at the billing period. Video-to-sound is marked coming soon, with planned clip upload and scene-matched audio. Sonicker lists commercial use as restricted.