​
Protecting a pre-recorded audio file using the Voice Harbor’s Python SDK

Prerequisite: Ensure that you have Python 3.6+ installed and an active Voice Harbor account with API access.

​
Step 1: Install Required Libraries

Before you start, you’ll need to install the required libraries for interacting with the Voice Harbor API.

Python SDK

Start using our Python SDK to connect with Voice Harbor and implement voice solutions

​
From Source

  1. Clone the Voice Harbor SDK repository from Github.
  2. Change into the project directory.
  3. Install the package in editable mode using pip:
  pip install -e .

​
Step 2: Set Up Your API Key

To authenticate with the Voice Harbor API, you’ll need to set your API key. Obtain your API key from your Voice Harbor dashboard. To set up the developer token for authentication, use the following code: 
BASE_URL = "https://voiceharbor.ai"
admin_token = "your_admin_token_here"

# Create a developer token for usage with Voice Harbor
usage_token = VoiceHarborClient.create_developer_token(BASE_URL, admin_token)

# Received developer token stored below:
print(f"Developer token stored: ./credentials/VoiceHarbor_Developer.credential.<date>.yaml")

​
Step 3: Set Up the Client and Create a Job

Once you have the necessary setup, you can create a job on the server and interact with the API. Here’s how to do it: 
BASE_URL = "https://voiceharbor.ai"
usage_token = "your_usage_token_here"

# Create a new job on the server via the class method.
# Create a new job immediately.
job_id = VoiceHarborClient.create_job(BASE_URL, usage_token)
print(f"Job created with ID: {job_id}")

​
Step 4: Initialize the Client and Submit Job Files

Next, initialize the client and define the parameters for your job, including the files you want to submit for transcription.
Not sure which model best fits your data? Read more in Advanced vs. Mini.
# Initialize the client with the new job_id and input directory.
client = VoiceHarborClient(
    base_url=BASE_URL,
    job_id=job_id,
    token=usage_token,  # Ensure correct token is used here
    inputs_dir="./inputs"
)

# Build job parameters (e.g., list of agents and any other details).
job_params = {
    "model": "mini",
    "files": []  # The submit_files method will append uploaded file names.
}

# Upload input files.
job_params = client.submit_files(job_params)

​
Step 5: Submit Job and Download Results

Now, submit the job and wait for the transcription results. Here’s how to complete the process:
It’s recommended to use the a scheduled download approach if submitting larger amount of volume with advanced models. Read Documentation.
# Immediately submit the job file (YAML)
job_file = client.submit_job(job_params)
print(f"Job file submitted: {job_file}")

# Wait for and download the processed results.
downloaded_results = client.download_results(output_dir="./results")
print("Downloaded results:", downloaded_results)

​
Results example

​
Troubleshooting

If you encounter any issues while transcribing the audio, check the following:
  • Ensure that the audio file path is correct and the file is accessible.
  • Check the format of the audio file. Voice Harbor currently supports formats like WAV, MP3, and FLAC.

​
Additional Resources

For more information, you can refer to the following:

​
Next Steps

If you’re interested in additional use cases or need help with more advanced features, don’t hesitate to explore our comprehensive Voice Harbor Documentation.