Bark can generate highly realistic, multilingual speech as well as other audio – including music, background noise, and simple sound effects.
Not just that Bark can also:
Produce nonverbal communication like laughing, sighing, and crying.
The best part is that it’s free and fully open-sourced.
It’s not just generate speech, it can also generate melodies/songs just from your text prompts. You just need to add music notes around your lyrics.
Prompt:
” ♪ In the jungle, the mighty jungle, the lion barks tonight ♪ “
You can provide certain speaker prompts such as NARRATOR, MAN, WOMAN, etc.
Demo: