Async vs MMAudio

Async is an online AI video editor where users create and edit videos through chat. It can remove filler, pauses, repetitions, bad takes, and awkward moments. Magic Dust reduces background noise and clarifies voices, while chat can generate B-roll, visuals, scenes, or music within an edit. Users can add subtitles and turn moments from longer videos into short-form clips. Async presents the workflow for ads, vlogs, explainers, podcasts, and other formats, and says it is built for creators and teams. Its browser-based remote interview feature supports up to 10 participants with separate tracks; local recording and automatic transcription are also listed. The Voice API supports text-to-speech and speech-to-text, including streaming over WebSockets. Async is available on the web and iOS, with no Android version listed. The Free plan is free and includes 10 lifetime AI credits, one hour of media upload to AI chat, exports up to 720p, and 2 GB storage. Paid pricing starts at $11.99/mo (annual).

MMAudio generates audio from video or text, with a synchronization module that aligns generated sound to video frames. Its command-line demo and Gradio interface support video-to-audio and text-to-audio generation. The interface also has an experimental image-to-audio mode: the model was not trained for image input, and the demo turns a still image into a video for processing. The project is free, with repository code under the MIT license and pretrained checkpoints under CC-BY-NC 4.0. It runs on Linux or in a self-hosted setup. Installation calls for Python 3.9 or later and PyTorch 2.5.1 or later, with corresponding torchvision and torchaudio; the project says it has only been tested on Ubuntu. In the default large_44k_v2 configuration, inference in 16-bit mode uses around 6 GB of GPU memory. The demo saves audio as FLAC and video as MP4, with an eight-second default duration. Output may include unintelligible speech-like sounds or background music, and unfamiliar concepts can be difficult for the model.