Capturing Audio and Voice

import { readFileSync } from "node:fs";
import { openai } from "@ai-sdk/openai";
import { generateText } from "ai";
import { setupObservability } from "langwatch/observability/node";

setupObservability({ serviceName: "voice-service" });

const data = readFileSync("call.wav").toString("base64");

const { text } = await generateText({
  model: openai.chat("gpt-audio-mini"),
  messages: [
    {
      role: "user",
      content: [
        { type: "text", text: "What does the caller ask for?" },
        { type: "file", data, mediaType: "audio/wav", filename: "call.wav" },
      ],
    },
  ],
  experimental_telemetry: { isEnabled: true },
});

console.log(text);

import { readFileSync } from "node:fs";
import OpenAI from "openai";
import { getLangWatchTracer } from "langwatch";
import { setupObservability } from "langwatch/observability/node";

setupObservability({ serviceName: "voice-service" });

const tracer = getLangWatchTracer("voice-service");
const client = new OpenAI();

const transcribe = async (prompt: string, path: string): Promise<string> => {
  return await tracer.withActiveSpan("TranscribeCall", async (span) => {
    span.setType("llm");

    const encoded = readFileSync(path).toString("base64");
    const completion = await 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 ?? "";
  });
};

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