AssemblyAI STT

The AssemblyAI STT provider enables your agent to use AssemblyAI's real-time WebSocket API for fast and accurate speech-to-text conversion.

Installation

Install the AssemblyAI-enabled VideoSDK Agents package:

pip install "videosdk-plugins-assemblyai"

Authentication

The AssemblyAI plugin requires an AssemblyAI API key.

Set ASSEMBLYAI_API_KEY in your .env file.

Importing

from videosdk.plugins.assemblyai import AssemblyAISTT

Example Usage

from videosdk.plugins.assemblyai import AssemblyAISTT
from videosdk.agents import CascadingPipeline

# Initialize the AssemblyAI STT model
stt = AssemblyAISTT(
    api_key="your-assemblyai-api-key",
    language_code="en_us"
)

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

note

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

Configuration Options

• api_key: Your AssemblyAI API key (required, can also be set via ASSEMBLYAI_API_KEY environment variable).
• language_code: The language code for transcription (e.g., "en_us", "es").

Additional Resources

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

• Python package: The videosdk-plugins-assemblyai package on PyPI.

• GitHub repo: View the source or contribute to the VideoSDK AssemblyAI STT plugin.

• AssemblyAI Docs: AssemblyAI's official real-time streaming transcription documentation.