Azure OpenAI STT

The Azure OpenAI STT provider enables your agent to use Azure OpenAI's speech-to-text models (like Whisper) for converting audio input to text.

Installation

Install the Azure OpenAI-enabled VideoSDK Agents package:

pip install "videosdk-plugins-openai"

Authentication

The Azure OpenAI plugin requires either an Azure OpenAI API key.

Set AZURE_OPENAI_API_KEY , AZURE_OPENAI_ENDPOINT and OPENAI_API_VERSION in your .env file.

Importing

from videosdk.plugins.openai import OpenAISTT

Example Usage

from videosdk.plugins.openai import OpenAISTT
from videosdk.agents import CascadingPipeline

# Initialize the Azure OpenAI STT model
stt = OpenAISTT.azure(
    azure_deployment="gpt-4o-transcribe",
    language="en",
)

#  Add stt to cascading pipeline
pipeline = CascadingPipeline(stt=stt)

note

When using .env file for credentials, don't pass them as arguments to model instances or context objects. The SDK automatically reads environment variables, so omit api_key, videosdk_auth, and other credential parameters from your code.

Configuration Options

• azure_deployment: The OpenAI deployment ID to use (by default it is model name: e.g., "gpt-4o-mini-transcribe", "gpt-4o-transcribe")
• api_key: Your Azure OpenAI API key (can also be set via environment variable)
• azure_endpoint: Your Azure OpenAI Deployment Endpoint URL (can also be set via environment variable)
• api_version: Your Azure OpenAI API version (can also be set via environment variable)
• language: (str) Language code for transcription (default: "en")

Additional Resources

The following resources provide more information about using OpenAI with VideoSDK Agents SDK.

SDK Reference

GitHub Repository

Python Package