Capturing Audio and Voice

import base64
import langwatch
from openai import OpenAI

langwatch.setup()


@langwatch.trace(name="transcribe call")
def transcribe(prompt: str, path: str) -> str:
    client = OpenAI()
    langwatch.get_current_trace().autotrack_openai_calls(client)

    encoded = base64.b64encode(open(path, "rb").read()).decode("utf-8")
    completion = client.chat.completions.create(
        model="gpt-audio-mini",
        messages=[
            {
                "role": "user",
                "content": [
                    {"type": "text", "text": prompt},
                    {
                        "type": "input_audio",
                        "input_audio": {"data": encoded, "format": "wav"},
                    },
                ],
            }
        ],
    )
    return completion.choices[0].message.content or ""


transcribe("What does the caller ask for?", "call.wav")

import asyncio

import langwatch
from google.adk import Agent, Runner
from google.adk.sessions import InMemorySessionService
from google.genai import types
from openinference.instrumentation.google_adk import GoogleADKInstrumentor

langwatch.setup(instrumentors=[GoogleADKInstrumentor()])

APP_NAME = "call-reader"
USER_ID = "caller-1"
SESSION_ID = "session-1"


def transcribe(prompt: str, path: str) -> str:
    agent = Agent(
        name="call_agent",
        model="gemini-2.5-flash",
        instruction="Answer the user's question about the attached recording directly.",
    )
    session_service = InMemorySessionService()
    asyncio.run(
        session_service.create_session(
            app_name=APP_NAME, user_id=USER_ID, session_id=SESSION_ID
        )
    )
    runner = Runner(agent=agent, app_name=APP_NAME, session_service=session_service)

    message = types.Content(
        role="user",
        parts=[
            types.Part(text=prompt),
            types.Part.from_bytes(
                data=open(path, "rb").read(), mime_type="audio/wav"
            ),
        ],
    )

    for event in runner.run(
        user_id=USER_ID, session_id=SESSION_ID, new_message=message
    ):
        if event.is_final_response():
            return event.content.parts[0].text
    return ""


transcribe("What does the caller ask for?", "call.wav")