Bark

Bark is a transformer text-to-audio model from Suno that generates speech, music, background noise, and short sound effects in many languages from a single text prompt. Unlike conventional TTS systems, it is fully generative and can produce nonverbal vocalizations such as laughing, sighing, and crying. Pretrained model checkpoints are released for research and commercial use; outputs can diverge from prompts in unpredictable ways.