MultiVoice Tester: Automated Text-to-Speech Voice Sampling for Audiobooks

[Vodou4460]

MultiVoice Tester: Automated Text-to-Speech Voice Sampling for Audiobooks

# Speaker Name Iteration Script for Text-to-Speech Conversion

# List of speaker names to iterate over
# This list contains various speaker names used in the text-to-speech conversion process.
speaker_names = [
    'Claribel Dervla', 'Daisy Studious', 'Gracie Wise', 'Tammie Ema', 'Alison Dietlinde',
    'Ana Florence', 'Annmarie Nele', 'Asya Anara', 'Brenda Stern', 'Gitta Nikolina',
    'Henriette Usha', 'Sofia Hellen', 'Tammy Grit', 'Tanja Adelina', 'Vjollca Johnnie',
    'Andrew Chipper', 'Badr Odhiambo', 'Dionisio Schuyler', 'Royston Min', 'Viktor Eka',
    'Abrahan Mack', 'Adde Michal', 'Baldur Sanjin', 'Craig Gutsy', 'Damien Black',
    'Gilberto Mathias', 'Ilkin Urbano', 'Kazuhiko Atallah', 'Ludvig Milivoj', 'Suad Qasim',
    'Torcull Diarmuid', 'Viktor Menelaos', 'Zacharie Aimilios', 'Nova Hogarth', 'Maja Ruoho',
    'Uta Obando', 'Lidiya Szekeres', 'Chandra MacFarland', 'Szofi Granger', 'Camilla Holmström',
    'Lilya Stainthorpe', 'Zofija Kendrick', 'Narelle Moon', 'Barbora MacLean', 'Alexandra Hisakawa',
    'Alma María', 'Rosemary Okafor', 'Ige Behringer', 'Filip Traverse', 'Damjan Chapman',
    'Wulf Carlevaro', 'Aaron Dreschner', 'Kumar Dahl', 'Eugenio Mataracı', 'Ferran Simen',
    'Xavier Hayasaka', 'Luis Moray', 'Marcos Rudaski'
]
# Thanks to https://github.com/rejuce/CoquiTTS_XTTS_Examples/blob/main/runAllSpeakers.sh

# Path to the text-to-speech conversion script
script_path = 'epub2tts.py'

# Input file for text-to-speech conversion
input_file = 'exemple.txt'

# Additional parameters for the conversion script
engine = 'xtts'  # Specify the TTS engine to be used
language = 'fr'  # Set the language for the TTS conversion
minratio = '0'   # Minimum ratio parameter (specific to your TTS script)

# Loop through each speaker name and execute the script for each one
# This loop constructs and executes a command for each speaker,
# running the text-to-speech conversion with the specified parameters.
for speaker in speaker_names:
    command = f"python3 {script_path} {input_file} --engine {engine} --speaker '{speaker}' --language '{language}' --minratio '{minratio}'"
    print(f"Executing command: {command}")
    get_ipython().system(command)

# Note: This script is intended to be run in a Jupyter Notebook environment.
# If running in a different environment, replace 'get_ipython().system(command)'
# with 'subprocess.run(command, shell=True)' or a similar command execution method.

Script Explanation :

1. Purpose of the Script: This script is crafted to streamline the process of text-to-speech (TTS) conversion using diverse speaker voices. It's especially helpful for audiobook creators who face challenges in selecting the ideal voice for their audiobooks. By automating TTS conversions with different speakers, the script aids in identifying the voice that best suits the content and style of the audiobook.

2. How It Works: The script iterates over a pre-defined list of speaker names, executing a TTS conversion for each speaker on a sample text file. This allows users to efficiently test and compare different speaker outputs. The sample text can be a general example or key phrases from the actual text intended for conversion, providing a realistic preview of each speaker's suitability.

3. Customization and Flexibility: Users can modify the list of speaker names, the path to the TTS script (script_path), the input file (input_file), and other parameters to fit their specific needs. This flexibility is key for tailoring the script to various types of audiobooks and content.

4. Potential for Multi-Speaker Conversion: While current technology may not fully support multi-speaker conversion, this script lays the groundwork for such advancements. Its capability to automate speaker selection hints at the possibility of developing multi-speaker audiobooks in the future, enhancing the listening experience with varied voices.

5. Execution Environment: This script is designed for a Jupyter Notebook environment. For use in other environments, the command execution method should be changed to something like subprocess.run(command, shell=True).

6. User Guide: To use the script, simply populate the speaker_names list with desired TTS voices, specify the script path, and choose an input file. The script will handle the rest, presenting you with audio samples from each speaker to aid in your selection process.