MMAudio is a research project on multimodal joint training for video-to-audio synthesis. It generates synchronized audio given video and/or text inputs. The work is presented at CVPR 2025 by authors from the University of Illinois Urbana-Champaign and Sony.
AudioLDM is a text-to-audio system built on a latent space that learns continuous audio representations from CLAP latents. It generates text-conditional sound effects, human speech and music, and enables zero-shot text-guided audio style transfer, inpainting and super-resolution.
AudioArena is a site for benchmarking and comparing voice models through real conversations. It offers AudioAgentBench, a set of six static multi-turn voice agent benchmarks, scored across five dimensions, and lets users select a benchmark, model, and run to view turn-by-turn transcripts.
A transcription API built on OpenAI Whisper that converts audio and video files to text. It supports file uploads and remote URLs, multiple output formats, and model size selection for speed versus accuracy. A no-code dashboard offers drag-and-drop transcription. Pricing is pay-as-you-go with credit bundles, and files auto-delete after 24 hours.
Works with speech, voice, music or other audio using machine-learning models.
Endel is a mobile app that provides personalized soundscapes intended to help with focus, relaxation and sleep, backed by neuroscience. The app adapts sounds in real time using inputs such as time of day, weather, heart rate and location. It also offers versions for Apple Watch, Amazon Alexa, TV, desktop and streaming platforms.
Readwise Reader is a read-it-later app that saves articles, newsletters, RSS feeds, PDFs, EPUBs, YouTube videos and Twitter threads in one place. It offers web highlighting and annotation through a browser extension and integrates with the Readwise app, which resurfaces highlights via Daily Review and exports them to note-taking tools.
Community notes
Be the first to share how this project worked for you.
Sign in with a verified account to leave a review or join the discussion.
Sign in to reviewKeep exploring
AudioLDM is a text-to-audio system built on a latent space that learns continuous audio representations from CLAP latents. It generates text-conditional sound effects, human speech and music, and enables zero-shot text-guided audio style transfer, inpainting and super-resolution.
AudioArena is a site for benchmarking and comparing voice models through real conversations. It offers AudioAgentBench, a set of six static multi-turn voice agent benchmarks, scored across five dimensions, and lets users select a benchmark, model, and run to view turn-by-turn transcripts.
A transcription API built on OpenAI Whisper that converts audio and video files to text. It supports file uploads and remote URLs, multiple output formats, and model size selection for speed versus accuracy. A no-code dashboard offers drag-and-drop transcription. Pricing is pay-as-you-go with credit bundles, and files auto-delete after 24 hours.
Works with speech, voice, music or other audio using machine-learning models.
Endel is a mobile app that provides personalized soundscapes intended to help with focus, relaxation and sleep, backed by neuroscience. The app adapts sounds in real time using inputs such as time of day, weather, heart rate and location. It also offers versions for Apple Watch, Amazon Alexa, TV, desktop and streaming platforms.
Readwise Reader is a read-it-later app that saves articles, newsletters, RSS feeds, PDFs, EPUBs, YouTube videos and Twitter threads in one place. It offers web highlighting and annotation through a browser extension and integrates with the Readwise app, which resurfaces highlights via Daily Review and exports them to note-taking tools.
