Transcription Agent

Give an agent GroqTools to transcribe a hosted WAV file to English.

transcription_agent.py

"""Run `uv pip install groq` to install dependencies."""

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

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------

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")

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------

if __name__ == "__main__":
    pass

Run the Example

1. Set up your virtual environment

   Mac

   uv venv --python 3.12
   source .venv/bin/activate
   
2. Install dependencies

   uv pip install -U agno groq openai
   
3. Export your API keys

   Mac/Linux

   export GROQ_API_KEY="your_groq_api_key_here"
   export OPENAI_API_KEY="your_openai_api_key_here"
   
4. Run the example

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

   python transcription_agent.py
   

Full source: cookbook/90_models/groq/transcription_agent.py