audio_streaming.py
"""
Audio Streaming
=============================
Audio Streaming.
"""
import base64
import wave
from typing import Iterator
from agno.agent import Agent, RunOutputEvent
from agno.models.openai import OpenAIChat
# Audio Configuration
SAMPLE_RATE = 24000 # Hz (24kHz)
CHANNELS = 1 # Mono (Change to 2 if Stereo)
SAMPLE_WIDTH = 2 # Bytes (16 bits)
# Provide the agent with the audio file and audio configuration and get result as text + audio
# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------
agent = Agent(
model=OpenAIChat(
id="gpt-audio",
modalities=["text", "audio"],
audio={
"voice": "alloy",
"format": "pcm16",
}, # Only pcm16 is supported with streaming
),
)
# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
output_stream: Iterator[RunOutputEvent] = agent.run(
"Tell me a 10 second story", stream=True
)
filename = "tmp/response_stream.wav"
# Open the file once in append-binary mode
with wave.open(str(filename), "wb") as wav_file:
wav_file.setnchannels(CHANNELS)
wav_file.setsampwidth(SAMPLE_WIDTH)
wav_file.setframerate(SAMPLE_RATE)
# Iterate over generated audio
for response in output_stream:
response_audio = response.response_audio # type: ignore
if response_audio:
if response_audio.transcript:
print(response_audio.transcript, end="", flush=True)
if response_audio.content:
try:
pcm_bytes = base64.b64decode(response_audio.content)
wav_file.writeframes(pcm_bytes)
except Exception as e:
print(f"Error decoding audio: {e}")
print()
Run the Example
1
Set up your virtual environment
uv venv --python 3.12
source .venv/bin/activate
uv venv --python 3.12
.venv\Scripts\activate
2
Install dependencies
uv pip install -U agno openai
3
Export your OpenAI API key
export OPENAI_API_KEY="your_openai_api_key_here"
$Env:OPENAI_API_KEY="your_openai_api_key_here"
4
Create the output directory
Create the directory used for the WAV file:
python -c "from pathlib import Path; Path('tmp').mkdir(parents=True, exist_ok=True)"
5
Run the example
Save the code above as
audio_streaming.py, then run:python audio_streaming.py