Add audio transcription to command execution by field

[Josh-XT]

Add audio transcription to command execution by field

The variables is_m4a_audio and is_wav_audio can be used to target fields in command execution that are populated with base64 audio that needs transcribed to text.

Example usage

from agixtsdk import AGiXTSDK

sdk = AGiXTSDK( base_uri="http://localhost:7437", api_key="")
base64_audio = get_base64_audio("Today has been a good day!")

response = sdk.execute_command(
    agent_name="gpt4free",
    command_name="Write to File",
    command_args={
        "filename": "notes.txt"
        "text": base64_audio,
        "is_m4a_audio": "text",
    },
    conversation_name="Test Conversation",
)

print(response)