Bark
Transformer text-to-audio model generating speech, music, sound effects and nonverbal sounds.
| Language | Python |
|---|---|
| Category | ML & generative |
| License | MIT |
| Platforms | macOS Windows Linux |
| Install | pip install git+https://github.com/suno-ai/bark.git |
| First released | 2023 |
| Maintained | Not actively maintained (last activity 2024) |
| Links | Source |
Strengths
- Expressive multilingual speech plus music/SFX and nonverbals
- Simple Python API; MIT-licensed code
- Built-in speaker/voice presets
Limitations
- Repo largely inactive since 2024
- GPU recommended; research-quality, not production TTS
Best for
Prototyping generative speech and sound from text prompts.
Minimal example
from bark import generate_audio, SAMPLE_RATE, preload_models
preload_models()
audio = generate_audio("Hello, I like pizza. [laughs]")