Bark

Bark

Bark is a transformer-based text-to-audio model created by Suno AI. Unlike traditional TTS systems, Bark generates highly natural speech with emotions, music, background noise, and even non-verbal sounds like laughing or sighing — all from a single text prompt.

Key Features

• Generates speech, music beds, and ambient sounds from free-form text prompts
• 100+ speaker presets across languages and accents; clone any voice with a short sample
• Non-verbal audio: [laughs], [sighs], [music], [gasps] markup in prompts
• Multilingual: English, German, Spanish, French, Hindi, Italian, Japanese, Korean, Polish, Portuguese, Russian, Turkish, Chinese
• HuggingFace integration for one-line model loading

Quick Start

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

from bark import SAMPLE_RATE, generate_audio, preload_models
from scipy.io.wavfile import write as write_wav

preload_models()
audio_array = generate_audio(
    "Hello, I'm Bark! [laughs] Isn't this amazing?"
)
write_wav("output.wav", SAMPLE_RATE, audio_array)

npx ai-supply add bark-text-to-speech

Curated mirror of the open-source Bark (MIT). Get it from the source.