Audio to Text Transcription

This example demonstrates how to create an agent that can transcribe audio conversations, identifying different speakers and providing accurate transcriptions.

Code

audio_to_text.py

import requests
from agno.agent import Agent
from agno.media import Audio
from agno.models.google import Gemini

agent = Agent(
    model=Gemini(id="gemini-2.0-flash-exp"),
    markdown=True,
)

url = "https://agno-public.s3.us-east-1.amazonaws.com/demo_data/QA-01.mp3"

response = requests.get(url)
audio_content = response.content

# Give a transcript of this audio conversation. Use speaker A, speaker B to identify speakers.

agent.print_response(
    "Give a transcript of this audio conversation. Use speaker A, speaker B to identify speakers.",
    audio=[Audio(content=audio_content)],
    stream=True,
)

Usage

1. Create a virtual environment

   Open the Terminal and create a python virtual environment.

   Mac

   python3 -m venv .venv
   source .venv/bin/activate
   
2. Install libraries

   pip install -U agno google-generativeai requests
   
3. Export your GOOGLE API key

   Mac/Linux

     export GOOGLE_API_KEY="your_google_api_key_here"
   
4. Create a Python file

   Create a Python file and add the above code.

   touch audio_to_text.py
   
5. Run Agent

   Mac

   python audio_to_text.py
   
6. Find All Cookbooks

   Explore all the available cookbooks in the Agno repository. Click the link below to view the code on GitHub:

   Agno Cookbooks on GitHub