Version: 2.0.0

Python

Learn how to import a phoneme library from a CSV using the Resemble API AI platform with Python.

In order to best use this guide ensure that you have:

Signed up for a Resemble.ai account and confirmed your e-mail
Obtained your API key for use with the API - for additional information see the Authentication page

Guide

First, you will need to initialize your Python project, it’s virtual environment.

# Create virtual environment
python3 -m venv venv

# Activate virtual environment
source venv/bin/activate

With your project setup, we can install the Resemble Python SDK via pip install and freeze our dependency list for later use:

# Install Resemble python SDK
pip install resemble

# Freeze dependencies
pip freeze > requirements.txt

Create a new [main.py](http://main.py) file which will contain our script to import phonemes.

Initialize the script by creating a basic run_main function and fill in your [main.py](http://main.py) with the code snippet below.

# resemble-import-phonemes/main.py

# This is the main function that contains the example
def run_main():
    # TODO: Fill me in!

if __name__ == '__main__':
    run_main()

Next, import the Resemble class from the resemble sdk, the argparse, and os module from Python’s standard library and add a setup function to initialize the API client called initialize_resemble_client:

# resemble-import-phonemes/main.py
import os
import argparse
from resemble import Resemble

# This function sets up the Resemble Python SDK
def initialize_resemble_client():
    try:
        # Attempt to retrieve the value of the environment variable
        resemble_api_key = os.environ['RESEMBLE_API_KEY']

        Resemble.api_key(resemble_api_key)
    except KeyError:
        # If the environment variable is not found, raise an error
        raise EnvironmentError(f"The 'RESEMBLE_API_KEY' environment variable is not set.")

# This is the main function that contains the example
def run_main():
    # TODO: Fill me in!

# -- snipped --

Notice that the Python script expects the environment variable RESEMBLE_API_KEY to be present containing the necessary API key.

Next, build the import_phonemes function responsible for parsing a CSV containing your phonemes and uploading to the API (don’t forget to import csv ).

Add the following code snippet below to main.py file.

# resemble-import-phonemes/main.py

import os
from resemble import Resemble
import csv

def import_phonemes(csv_file_path):
    # Keep track of successful and failed imports (possibly due to already existing)
    successful_imports = 0
    failed_imports = 0

    try:
        with open(csv_file_path, 'r') as file:
            # Create a CSV reader object
            reader = csv.reader(file)

            # Skip the header row if it exists
            next(reader, None)

            # Iterate over each row in the CSV file
            for row in reader:
                # Ensure the row has at least two elements (word and phonetic_transcription)
                if len(row) >= 2:
                    word, phonetic_transcription = row[0], row[1]

                    try:
                        # Make a POST request to create a new widget entry
                        response = Resemble.v2.phonemes.create(word, phonetic_transcription)
                        if response['success']:
                            successful_imports += 1
                            print(f"Imported phoneme pair: {word} and {phonetic_transcription}")
                        else:
                            # Failed to import for some reason
                            raise Exception(response)

                    except Exception as e:
                        failed_imports += 1

                        print(f"ERROR: Could not import phoneme pair: {word} and {phonetic_transcription} - {e}")

    except FileNotFoundError:
        print(f"ERROR: File not found - {csv_file_path}")

    # Print summary
    print(f"\nCompleted\nSuccessfully imported phonemes: {successful_imports}\nFailed to import phonemes: {failed_imports}")

# This function sets up the Resemble Python SDK
def initialize_resemble_client():
    # -- snipped --

# -- snipped --

In the above snippet, the import_phonemes file parses through the a CSV in the following format and creates a pair entry using the Resemble API. Note the headers will be skipped!

# example-phoneme.csv
word,phonentic_transcription
vodaphone,voduhphone
cosmic,kozmik

Once you have completed the import_phonemes , function update run_main function to accept an input file from the command line and execute the import_phonemes process.

# -- snipped -

# This is the main function that contains the example
def run_main(arguments):
    # Initialize the client using the environment variable RESEMBLE_API_KEY set
    initialize_resemble_client()
    # Run the voice creation function to call the Resemble API
    import_phonemes(arguments['csv_file'])

parser = argparse.ArgumentParser(description="A script that imports phonemes using Resemble AI")

# Add option flags to the parser
parser.add_argument("--csv-file", required=True, help="The CSV file containing phonemes to import")

# Parse the command-line arguments
args = parser.parse_args()

arguments = { 'csv_file': args.csv_file }

if __name__ == '__main__':
    run_main(arguments)

Finally, test your script by running the same command via CLI as before:

# Be sure to prepend your API key to the command
RESEMBLE_API_KEY=... python3 main.py --csv-file path/to/example-csv.csv

Imported phoneme pair: vodaphone and voduhphone
Imported phoneme pair: cosmic and kozmik

Completed
Successfully imported phonemes: 2
Failed to import phonemes: 0

Congratulations, you have successfully imported your phoneme library! To check the status of your library, you can programmatically access via the API or use the web application as well.

Python

Guide​

Guide