Bark

It is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multi-task model that can perform multilingual speech recognition as well as speech translation and language identification.

It is Stability AI’s first product for music and sound effect generation. Users can create original audio by entering a text prompt and a duration, generating audio in high-quality, 44.1 kHz stereo.

It is a 1.2B parameter base model trained on 100K hours of speech for TTS (text-to-speech). It empowers developers and businesses to better connect with their audiences at scale.