Bark
Suno’s generative audio model: speech, music snippets and sound effects.
- Star 数
- 39.3K
- Fork 数
- 4.7K
- 未关闭 Issue
- 269
- 最近提交
- 2024-08-19
数据来自 GitHub API · 更新于 2026-10-15
Bark 是什么？
Bark is a transformer-based text-to-audio model that can produce multilingual speech, nonverbal sounds like laughing and sighing, and simple music. It is MIT licensed, though no longer actively developed.
主要功能
- Multilingual speech with nonverbal cues
- Simple music and sound effects
- Speaker presets
系统要求
- 平台
- Windows · macOS · Linux
- 显卡
- NVIDIA recommended
- 显存
- ~12 GB full; ~8 GB with small models
如何安装 Bark
根据项目 README 整理。开源项目更新很快，请以 GitHub 页面上的最新说明为准。
pip
- 1Install from GitHub.
pip install git+https://github.com/suno-ai/bark.git - 2Generate audio in Python.
from bark import SAMPLE_RATE, generate_audio, preload_models from scipy.io.wavfile import write as write_wav preload_models() audio = generate_audio("Hello, my name is Suno. [laughs] And I like pizza.") write_wav("bark.wav", SAMPLE_RATE, audio)
优势
- Expressive, fun outputs
- MIT license
不足
- Unpredictable results
- No longer maintained
Bark 替代品对比
| 软件 | Star 数 | 许可证 | 平台 | 显存 |
|---|---|---|---|---|
| Bark Suno’s generative audio model: speech, music snippets and sound effects. | 39.3K | MIT | ~12 GB full; ~8 GB with small models | |
| ChatTTS Conversational TTS for dialogue, with laughter and pauses. | 39.9K | AGPL-3.0 | 4 GB+ | |
| Kokoro A tiny 82M-parameter TTS model with surprisingly natural voices. | 9.3K | Apache-2.0 | — | |
| AudioCraft (MusicGen) Meta’s library for MusicGen music generation and AudioGen sound effects. | 23.7K | MIT | 16 GB for the large model; smaller models need less | |
| Whisper OpenAI’s open-source speech recognition and translation model. | 110.5K | MIT | ~1 GB (tiny) to ~10 GB (large) | |
| whisper.cpp Whisper in plain C/C++ — fast on CPUs, Apple Silicon and mobile. | 54.4K | MIT | — |
常见问题
Bark 免费吗？
是的——Bark 是开源软件，采用 MIT 许可证。商用前请确认软件及模型权重的许可条款。
Bark 支持 Windows、Mac 和 Linux 吗？
Bark 支持：Windows, macOS, Linux。
运行 Bark 需要什么配置？
NVIDIA recommended. VRAM: ~12 GB full; ~8 GB with small models
如何安装 Bark？
1. Install from GitHub. 2. Generate audio in Python.
Bark 有哪些好的替代品？
常见替代品包括 ChatTTS, Kokoro, AudioCraft (MusicGen), Whisper，详见本页对比表。