Audio Inputs

Audio Processing enables applications to understand, generate, and reason over audio content using multimodal AI models. The audio processing works through the Completion endpoint and supports models that handle multiple modalities, including audio.

To get a full list of supported models, visit cortecs.ai and filter by the Audio tag.

Audio format support depends on the provider. Check the model documentation for details.

Python

from openai import OpenAI
import base64

client = OpenAI(
  base_url="https://api.cortecs.ai/v1",
  api_key="<API_KEY>",
)

# Load and encode audio file
with open("path/to/audio_test.mp3", "rb") as f:
    audio_base64 = base64.b64encode(f.read()).decode('utf-8')

chat_response = client.chat.completions.create(
    model="gemini-2.5-pro",
    messages=[{
        "role": "user",
        "content": [
            {
                "type": "text",
                "text": "What is this file about?"
            },
            {
                "type": "input_audio",
                "input_audio": {
                    "data": audio_base64,
                    "format": "mp3"
                }
            },
        ]
    }]
)

print(chat_response)

Node.js

import OpenAI from "openai";
import fs from "fs";

const client = new OpenAI({
  baseURL: "https://api.cortecs.ai/v1",
  apiKey: process.env.CORTECS_API_KEY,
});

// Load and encode audio file
const audioBuffer = fs.readFileSync("path/to/audio_test.mp3");
const audioBase64 = audioBuffer.toString("base64");

const chatResponse = await client.chat.completions.create({
  model: "gemini-2.5-pro",
  messages: [
    {
      role: "user",
      content: [
        {
          type: "text",
          text: "What is this file about?"
        },
        {
          type: "input_audio",
          input_audio: {
            data: audioBase64,
            format: "mp3"
          }
        }
      ]
    }
  ]
});

console.log(chatResponse);

Curl

curl https://api.cortecs.ai/v1/chat/completions \
  -H "Authorization: Bearer <API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-2.5-pro",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": "What is this file about?"
          },
          {
            "type": "input_audio",
            "input_audio": {
              "data": "<BASE64_AUDIO_DATA>",
              "format": "mp3"
            }
          }
        ]
      }
    ]
  }'

Note: For a dedicated speech-to-text endpoint, see the Audio Transcription page.