๐ Text-Prompted Generative Audio Model
Notice: Bark is Sunoโs open-source text-to-speech+ model. If you are looking for our text-to-music models, please visit us on our web page and join our community on Discord.
๐ Examples โข Suno Studio Waitlist โข Updates โข How to Use โข Installation โข FAQ
Bark is a transformer-based text-to-audio model created by Suno. 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, which are ready for inference and available for commercial use.
Bark was developed for research purposes. It is not a conventional text-to-speech model but instead a fully generative text-to-audio model, which can deviate in unexpected ways from provided prompts. Suno does not take responsibility for any output generated. Use at your own risk, and please act responsibly.
2023.05.01
ยฉ๏ธ Bark is now licensed under the MIT License, meaning itโs now available for commercial use!
โก 2x speed-up on GPU. 10x speed-up on CPU. We also added an option for a smaller version of Bark, which offers additional speed-up with the trade-off of slightly lower quality.
๐ Long-form generation, voice consistency enhancements and other examples are now documented in a new notebooks section.
๐ฅ We created a voice prompt library. We hope this resource helps you find useful prompts for your use cases! You can also join us on Discord, where the community actively shares useful prompts in the #audio-prompts channel.
๐ฌ Growing community support and access to new features here:
๐พ You can now use Bark with GPUs that have low VRAM (<4GB).
2023.04.20
from bark import SAMPLE_RATE, generate_audio, preload_models
from scipy.io.wavfile import write as write_wav
from IPython.display import Audio
# download and load all models
preload_models()
# generate audio from text
text_prompt = """
Hello, my name is Suno. And, uh โ and I like pizza. [laughs]
But I also have other interests such as playing tic tac toe.
"""
audio_array = generate_audio(text_prompt)
# save audio to disk
write_wav("bark_generation.wav", SAMPLE_RATE, audio_array)
# play text in notebook
Audio(audio_array, rate=SAMPLE_RATE)
text_prompt = """
์ถ์์ ๋ด๊ฐ ๊ฐ์ฅ ์ข์ํ๋ ๋ช
์ ์ด๋ค. ๋๋ ๋ฉฐ์น ๋์ ํด์์ ์ทจํ๊ณ ์น๊ตฌ ๋ฐ ๊ฐ์กฑ๊ณผ ์๊ฐ์ ๋ณด๋ผ ์ ์์ต๋๋ค.
"""
audio_array = generate_audio(text_prompt)
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.
text_prompt = """
Der Dreiรigjรคhrige Krieg (1618-1648) war ein verheerender Konflikt, der Europa stark geprรคgt hat.
This is a beginning of the history. If you want to hear more, please continue.
"""
audio_array = generate_audio(text_prompt)
text_prompt = """
โช In the jungle, the mighty jungle, the lion barks tonight โช
"""
audio_array = generate_audio(text_prompt)
Bark supports 100+ speaker presets across supported languages. You can browse the library of supported voice presets HERE, or in the code. The community also often shares presets in Discord.
Bark tries to match the tone, pitch, emotion and prosody of a given preset, but does not currently support custom voice cloning. The model also attempts to preserve music, ambient noise, etc.
text_prompt = """
I have a silky smooth voice, and today I will tell you about
the exercise regimen of the common sloth.
"""
audio_array = generate_audio(text_prompt, history_prompt="v2/en_speaker_1")
By default, generate_audio
works well with around 13 seconds of spoken text. For an example of how to do long-form generation, see ๐ Notebook ๐
python -m bark --text "Hello, my name is Suno." --output_filename "example.wav"
โผ๏ธ CAUTION โผ๏ธ Do NOT use pip install bark
. It installs a different package, which is not managed by Suno.
pip install git+https://github.com/suno-ai/bark.git
or
git clone https://github.com/suno-ai/bark
cd bark && pip install .
Bark is available in the ๐ค Transformers library from version 4.31.0 onwards, requiring minimal dependencies
and additional packages. Steps to get started:
pip install git+https://github.com/huggingface/transformers.git
from transformers import AutoProcessor, BarkModel
processor = AutoProcessor.from_pretrained("suno/bark")
model = BarkModel.from_pretrained("suno/bark")
voice_preset = "v2/en_speaker_6"
inputs = processor("Hello, my dog is cute", voice_preset=voice_preset)
audio_array = model.generate(**inputs)
audio_array = audio_array.cpu().numpy().squeeze()
from IPython.display import Audio
sample_rate = model.generation_config.sample_rate
Audio(audio_array, rate=sample_rate)
Or save them as a .wav
file using a third-party library, e.g. scipy
:
import scipy
sample_rate = model.generation_config.sample_rate
scipy.io.wavfile.write("bark_out.wav", rate=sample_rate, data=audio_array)
For more details on using the Bark model for inference using the ๐ค Transformers library, refer to the
Bark docs or the hands-on
Google Colab.
Bark has been tested and works on both CPU and GPU (pytorch 2.0+
, CUDA 11.7 and CUDA 12.0).
On enterprise GPUs and PyTorch nightly, Bark can generate audio in roughly real-time. On older GPUs, default colab, or CPU, inference time might be significantly slower. For older GPUs or CPU you might want to consider using smaller models. Details can be found in out tutorial sections here.
The full version of Bark requires around 12GB of VRAM to hold everything on GPU at the same time.
To use a smaller version of the models, which should fit into 8GB VRAM, set the environment flag SUNO_USE_SMALL_MODELS=True
.
If you donโt have 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.
Bark is fully generative text-to-audio model devolved for research and demo purposes. It follows a GPT style architecture similar to AudioLM and Vall-E and a quantized Audio representation from EnCodec. It is not a conventional TTS model, but instead a fully generative text-to-audio model capable of deviating in unexpected ways from any given script. Different to previous approaches, the input text prompt is converted directly to audio without the intermediate use of phonemes. It can therefore generalize to arbitrary instructions beyond speech such as music lyrics, sound effects or other non-speech sounds.
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!
[laughter]
[laughs]
[sighs]
[music]
[gasps]
[clears throat]
โ
or ...
for hesitationsโช
for song lyrics[MAN]
and [WOMAN]
to bias Bark toward male and female speakers, respectivelyLanguage | Status |
---|---|
English (en) | โ |
German (de) | โ |
Spanish (es) | โ |
French (fr) | โ |
Hindi (hi) | โ |
Italian (it) | โ |
Japanese (ja) | โ |
Korean (ko) | โ |
Polish (pl) | โ |
Portuguese (pt) | โ |
Russian (ru) | โ |
Turkish (tr) | โ |
Chinese, simplified (zh) | โ |
Requests for future language support here or in the #forums channel on Discord.
Bark is licensed under the MIT License.
Weโre developing a playground for our models, including Bark.
If you are interested, you can sign up for early access here.
import os
os.environ["SUNO_OFFLOAD_CPU"] = "True"
os.environ["SUNO_USE_SMALL_MODELS"] = "True"