test2.py

import numpy as np
from bark.api import generate_audio

from bark.generation import SAMPLE_RATE
from IPython.display import Audio


GEN_TEMP = 0.6
SPEAKER = "v2/en_speaker_6"
silence = np.zeros(int(0.25 * SAMPLE_RATE))  # quarter second of silence
speaker_lookup = {"Samantha": "v2/en_speaker_9", "John": "v2/en_speaker_2"}

# Script generated by chat GPT
script = """
Samantha: Hey, have you heard about this new text-to-audio model called "Bark"?

John: No, I haven't. What's so special about it?

Samantha: Well, apparently it's the most realistic and natural-sounding text-to-audio model out there right now. People are saying it sounds just like a real person speaking.

John: Wow, that sounds amazing. How does it work?

Samantha: I think it uses advanced machine learning algorithms to analyze and understand the nuances of human speech, and then replicates those nuances in its own speech output.

John: That's pretty impressive. Do you think it could be used for things like audiobooks or podcasts?

Samantha: Definitely! In fact, I heard that some publishers are already starting to use Bark to create audiobooks. And I bet it would be great for podcasts too.

John: I can imagine. It would be like having your own personal voiceover artist.

Samantha: Exactly! I think Bark is going to be a game-changer in the world of text-to-audio technology."""
script = script.strip().split("\n")
script = [s.strip() for s in script if s]

pieces = []
silence = np.zeros(int(0.5*SAMPLE_RATE))
for line in script:
    speaker, text = line.split(": ")
    audio_array = generate_audio(text, history_prompt=speaker_lookup[speaker], )
    pieces += [audio_array, silence.copy()]

Audio(np.concatenate(pieces), rate=SAMPLE_RATE).export("./out/test2", format="wav")