All models
expressive

Bark

MIT

Generates laughter, sighs, and music — the chaotic one

Bark, from Suno, is a generative text-to-audio model rather than a plain TTS system. Beyond multilingual speech it produces laughter, sighs, crying, music, and background sounds from inline cues — trading precise control for creative range. Still unmatched for character and chaos.

Voices

6 voices
Female
Speaker 3
english
Speaker 0
english
Speaker 9
english
Male
Speaker 6default
english
Speaker 5
english
Neutral
Announcer
english

The scripts

Neutral
“The quick brown fox jumps over the lazy dog near the riverbank.”
Emotional
“I can't believe you actually did it. This is incredible!”
Numbers & Dates
“On March 14th, 2025, the team raised $4.2 million at a 38% margin.”

Install

pip install git+https://github.com/suno-ai/bark.git

Bark FAQ

Do I need a GPU to run Bark?

For practical speeds, yes — plan on roughly 12 GB of VRAM. If you'd rather not manage a GPU, hosted access to every model in this directory is coming via OpenSpeech Cloud.

Can Bark clone voices?

Yes — Bark supports voice cloning from reference audio.

What license is Bark released under?

Bark is released under the MIT license. Always check the repository for the exact terms — some models license code and weights separately.

What languages does Bark support?

Bark supports English, Chinese, French, German, Hindi, Italian, Japanese, Korean, Polish, Portuguese, Russian, Spanish, Turkish.

Is there a hosted Bark API?

Yes — OpenSpeech Cloud is launching hosted, pay-per-minute access to Bark and every other model in this directory. No CUDA, Docker, or GPU needed.