Transcription Agent

Code

1from kern.agent import Agent
2from kern.models.openai import OpenAIResponses
3from kern.tools.models.groq import GroqTools
4
5url = "https://kern-public.s3.amazonaws.com/demo_data/sample_conversation.wav"
6
7agent = Agent(
8    name="Groq Transcription Agent",
9    model=OpenAIResponses(id="gpt-5.2"),
10    tools=[GroqTools(exclude_tools=["generate_speech"])],
11)
12
13agent.print_response(f"Please transcribe the audio file located at '{url}' to English")

Usage

Set up your virtual environment

1uv venv --python 3.12
2source .venv/bin/activate

1uv venv --python 3.12
2.venv\Scripts\activate

Set your API key

1export GROQ_API_KEY=xxx
2export OPENAI_API_KEY=xxx

Install dependencies

1uv pip install -U groq openai kern-ai

Run Agent

1python cookbook/11_models/groq/transcription_agent.py