Audio understanding

import base64
import json
import os

from openai import OpenAI

client = OpenAI(
    base_url="https://api.withhopper.com/v1",
    api_key=os.environ["HOPPER_API_KEY"],
)

audio = base64.b64encode(open("call.wav", "rb").read()).decode()

response = client.chat.completions.create(
    model="audio-perception-1",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Classify the primary expressed emotion in this clip."},
                {"type": "input_audio", "input_audio": {"data": audio, "format": "wav"}},
            ],
        }
    ],
    response_format={
        "type": "json_schema",
        "json_schema": {
            "name": "emotion",
            "strict": True,
            "schema": {
                "type": "object",
                "properties": {
                    "primary_emotion": {"enum": ["happy", "neutral", "sad"]},
                    "confidence": {"type": "number"},
                    "evidence": {"type": "string"},
                },
                "required": ["primary_emotion", "confidence", "evidence"],
            },
        },
    },
)
print(json.loads(response.choices[0].message.content))

import { readFile } from "node:fs/promises";
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.withhopper.com/v1",
  apiKey: process.env.HOPPER_API_KEY,
});

const audio = (await readFile("call.wav")).toString("base64");

const response = await client.chat.completions.create({
  model: "audio-perception-1",
  messages: [
    {
      role: "user",
      content: [
        { type: "text", text: "Did the customer get their task done? Reply as JSON with key done (boolean)." },
        { type: "input_audio", input_audio: { data: audio, format: "wav" } },
      ],
    },
  ],
  response_format: { type: "json_object" },
});
console.log(JSON.parse(response.choices[0].message.content!));

curl https://api.withhopper.com/v1/chat/completions \
  -H "Authorization: Bearer $HOPPER_API_KEY" \
  -H "Content-Type: application/json" \
  -d @- <<EOF
{
  "model": "audio-perception-1",
  "messages": [{
    "role": "user",
    "content": [
      {"type": "text", "text": "How would a human rate this call, 1 to 10? Reply with the number."},
      {"type": "input_audio", "input_audio": {"data": "$(base64 < call.wav | tr -d '\n')", "format": "wav"}}
    ]
  }]
}
EOF