Code
translation_agent.py
Prepare a corrected copy
The source fence is preserved for v2.7.2 fidelity. These packages and API keys cover its imports. Apply every change in the warning above before running it.1
Install dependencies
2
Set API keys
Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
Transcribe, translate, and regenerate audio with GroqTools.
playai-tts default, asks for music even though the tool generates speech, and saves WAV bytes with an .mp3 extension. Provide a real input file, select a current TTS model and voice, change the prompt to request speech, and save the output as .wav. See Groq model deprecations and Groq text to speech.import base64
from pathlib import Path
from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.tools.models.groq import GroqTools
from agno.utils.media import save_base64_data
path = "tmp/sample-fr.mp3"
agent = Agent(
name="Groq Translation Agent",
model=OpenAIChat(id="gpt-5.2"),
tools=[GroqTools()],
cache_session=True,
)
response = agent.run(
f"Let's transcribe the audio file located at '{path}' and translate it to English. After that generate a new music audio file using the translated text."
)
if response and response.audio:
base64_audio = base64.b64encode(response.audio[0].content).decode("utf-8")
save_base64_data(base64_audio, Path("tmp/sample-en.mp3")) # type: ignore
Install dependencies
uv pip install -U agno groq openai
Set API keys
export GROQ_API_KEY="your_groq_api_key_here"
export OPENAI_API_KEY="your_openai_api_key_here"
$Env:GROQ_API_KEY="your_groq_api_key_here"
$Env:OPENAI_API_KEY="your_openai_api_key_here"
Was this page helpful?