🐶 Bark

Bark is a multi-lingual TTS model created by Suno-AI. It can generate conversational speech as well as music and sound effects. It is architecturally very similar to Google’s AudioLM. For more information, please refer to the Suno-AI’s repo.

Acknowledgements

  • 👑Suno-AI for training and open-sourcing this model.

  • 👑gitmylo for finding the solution to the semantic token generation for voice clones and finetunes.

  • 👑serp-ai for controlled voice cloning.

Example use

See also

Voice cloning

text = "Hello, my name is Manmay , how are you?"

from TTS.tts.configs.bark_config import BarkConfig
from TTS.tts.models.bark import Bark

config = BarkConfig()
model = Bark.init_from_config(config)
model.load_checkpoint(config, checkpoint_dir="path/to/model/dir/", eval=True)

# Random speaker
output_dict = model.synthesize(text)

# Cloning a speaker.
output_dict = model.synthesize(text, speaker_wav="path/to/speaker.wav")

Using 🐸TTS API:

from TTS.api import TTS

# Load the model to GPU
# Bark is really slow on CPU, so we recommend using GPU.
tts = TTS("tts_models/multilingual/multi-dataset/bark").to("cuda")


# Clone voice and cache it with the custom ID `ljspeech`.
tts.tts_to_file(text="Hello, my name is Manmay , how are you?",
                file_path="output.wav",
                speaker_wav=["tests/data/ljspeech/wavs/LJ001-0001.wav"],
                speaker="ljspeech")


# When you run it again it uses the stored values to generate the voice.
tts.tts_to_file(text="Hello, my name is Manmay , how are you?",
                file_path="output.wav",
                speaker="ljspeech")


# random speaker
tts = TTS("tts_models/multilingual/multi-dataset/bark").to("cuda")
tts.tts_to_file("hello world", file_path="out.wav")

Using 🐸TTS Command line:

# Clone the `ljspeech` voice and cache it under that ID for later reuse without reference audio.
tts --model_name  tts_models/multilingual/multi-dataset/bark \
    --text "This is an example." \
    --out_path "output.wav" \
    --speaker_wav tests/data/ljspeech/wavs/*.wav
    --speaker_idx "ljspeech"

# Random voice generation
tts --model_name  tts_models/multilingual/multi-dataset/bark \
    --text "This is an example." \
    --out_path "output.wav"

Note

The authors of the Bark model provide a range of preset voices in .npz format that you can place into the voice_dir and then use in the speaker argument.

Important resources & papers

BarkConfig

Bark Model