STT overview

import requests
import os
import base64

with open("input.wav", "rb") as f:
    audio_content = base64.b64encode(f.read()).decode("utf-8")

response = requests.post(
    "https://api.inworld.ai/stt/v1/transcribe",
    headers={
        "Authorization": f"Basic {os.getenv('INWORLD_API_KEY')}",
        "Content-Type": "application/json",
    },
    json={
        "transcribeConfig": {
            "modelId": "inworld/inworld-stt-1",
            "language": "en",
            "audioEncoding": "LINEAR16",
        },
        "audioData": {"content": audio_content},
    },
)
response.raise_for_status()
print(response.json()["transcription"]["transcript"])

import fs from "fs";

const audioContent = fs.readFileSync("input.wav").toString("base64");

const response = await fetch("https://api.inworld.ai/stt/v1/transcribe", {
  method: "POST",
  headers: {
    Authorization: `Basic ${process.env.INWORLD_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    transcribeConfig: {
      modelId: "inworld/inworld-stt-1",
      language: "en",
      audioEncoding: "LINEAR16",
    },
    audioData: { content: audioContent },
  }),
});

const result = await response.json();
console.log(result.transcription.transcript);