audio-ai-timeline

Why we included this project

Keeping track of audio generation in 2023 meant following a steady stream of new models, and this timeline collects the notable ones into a single chronological table spanning music, speech, and sound synthesis. Each row links to the demo, paper, and code where available, so you can go from a name like MusicGen or Bark straight to its samples and implementation instead of hunting across separate sites. Because entries are ordered by release date, it is easy to see how text-to-audio and zero-shot speech approaches changed month to month, and the trained-model and Hugging Face links shorten the path to actually testing something. The curation is selective rather than exhaustive, which keeps the list skimmable for developers wanting a fast orientation to the space. It is a reference index rather than software you install, best treated as a starting map for exploring what came out and what to try next.