Bark is a transformer-based text-to-audio model created by [Suno](https://suno.ai). Bark can generate highly realistic, multilingual speech as well as other audio - including music, background noise and simple sound effects. The model can also produce nonverbal communications like laughing, sighing and crying. To support the research community, we are providing access to pretrained model checkpoints ready for inference.
[](https://colab.research.google.com/drive/1eJfA2XUa-mXwdMy7DoYKVYHI1iTd9Vkt?usp=sharing)
Bark supports various languages out-of-the-box and automatically determines language from input text. When prompted with code-switched text, Bark will even attempt to employ the native accent for the respective languages in the same voice.
Bark can generate all types of audio, and, in principle, doesn't see a difference between speech and music. Sometimes Bark chooses to generate text as music, but you can help it out by adding music notes around your lyrics.
Bark has the capability to fully clone voices - including tone, pitch, emotion and prosody. The model also attempts to preserve music, ambient noise, etc. from input audio. However, to mitigate misuse of this technology, we limit the audio history prompts to a limited set of Suno-provided, fully synthetic options to choose from for each language. Specify following the pattern: `{lang_code}_speaker_{number}`.
*Note: since Bark recognizes languages automatically from input text, it is possible to use for example a german history prompt with english text. This usually leads to english audio with a german accent.*
You can provide certain speaker prompts such as NARRATOR, MAN, WOMAN, etc. Please note that these are not always respected, especially if a conflicting audio history prompt is given.
On modern GPUs and PyTorch nightly, Bark can generate audio in roughly realtime. On older GPUs, default colab, or CPU, inference time might be 10-100x slower.
If you don't have new hardware available or if you want to play with bigger versions of our models, you can also sign up for early access to our model playground [here](https://3os84zs17th.typeform.com/suno-studio).
Similar to [Vall-E](https://arxiv.org/abs/2301.02111) and some other amazing work in the field, Bark uses GPT-style
models to generate audio from scratch. Different from Vall-E, the initial text prompt is embedded into high-level semantic tokens without the use of phonemes. It can therefore generalize to arbitrary instructions beyond speech that occur in the training data, such as music lyrics, sound effects or other non-speech sounds. A subsequent second model is used to convert the generated semantic tokens into audio codec tokens to generate the full waveform. To enable the community to use Bark via public code we used the fantastic
[EnCodec codec](https://github.com/facebookresearch/encodec) from Facebook to act as an audio representation.
Below is a list of some known non-speech sounds, but we are finding more every day. Please let us know if you find patterns that work particularly well on [Discord](https://discord.gg/DqEx7FGbFP)!
- [EnCodec](https://github.com/facebookresearch/encodec) for a state-of-the-art implementation of a fantastic audio codec
- [AudioLM](https://github.com/lucidrains/audiolm-pytorch) for very related training and inference code
- [Vall-E](https://arxiv.org/abs/2301.02111), [AudioLM](https://arxiv.org/abs/2209.03143) and many other ground-breaking papers that enabled the development of Bark
Bark is licensed under a non-commercial license: CC-BY 4.0 NC. The Suno models themselves may be used commercially. However, this version of Bark uses `EnCodec` as a neural codec backend, which is licensed under a [non-commercial license](https://github.com/facebookresearch/encodec/blob/main/LICENSE).
