Transcription Agent

Transcribe an audio file to English with GroqTools.

Code

transcription_agent.py

from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.tools.models.groq import GroqTools

url = "https://agno-public.s3.amazonaws.com/demo_data/sample_conversation.wav"

agent = Agent(
    name="Groq Transcription Agent",
    model=OpenAIChat(id="gpt-5.2"),
    tools=[GroqTools(exclude_tools=["generate_speech"])],
)

agent.print_response(f"Please transcribe the audio file located at '{url}' to English")

Usage

1. Set up your virtual environment

   Mac

   uv venv --python 3.12
   source .venv/bin/activate
   
2. Set your API key

   export GROQ_API_KEY=xxx
   export OPENAI_API_KEY=xxx
   
3. Install dependencies

   uv pip install -U groq openai agno
   
4. Run Agent

   Save the code above as transcription_agent.py, then run:

   python transcription_agent.py