OpenAI Agents SDK with Voice

OpenAI's function calling enables AI to take actions. Adding voice makes interactions natural.

What is Function Calling?

GPT-4 can intelligently decide when to call external functions:

• Get weather data
• Search databases
• Generate speech with LangVoice

Voice Integration Setup

from openai import OpenAI
from langvoice_sdk.tools import LangVoiceOpenAITools

client = OpenAI()
langvoice = LangVoiceOpenAITools(api_key="your-langvoice-key")

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {"role": "system", "content": "You are a voice assistant."},
        {"role": "user", "content": "Say hello in a friendly way"}
    ],
    tools=langvoice.get_tools(),
)

# Handle the tool call
if response.choices[0].message.tool_calls:
    for call in response.choices[0].message.tool_calls:
        result = langvoice.handle_call(call)
        langvoice.save_audio_from_result(result, "output.mp3")

Advanced: Streaming Responses

# Stream both text and generate audio
stream = client.chat.completions.create(
    model="gpt-4o",
    messages=messages,
    stream=True
)

# Collect response and speak
full_response = ""
for chunk in stream:
    if chunk.choices[0].delta.content:
        full_response += chunk.choices[0].delta.content
        print(chunk.choices[0].delta.content, end="")

# Generate audio at the end
audio = langvoice.generate(text=full_response, voice="heart")

Build powerful voice assistants with OpenAI and LangVoice!