Gladia

# pip install requests
import os, time, requests

API = "https://api.gladia.io/v2"
KEY = os.environ["GLADIA_API_KEY"]
HDR = {"x-gladia-key": KEY, "Content-Type": "application/json"}

# 1. submit
body = {
    "audio_url": "https://files.gladia.io/example/audio-transcription/split_infinity.wav",
    "diarization": True,
    "subtitles": True,
    "subtitles_config": {"formats": ["srt"]},
}
r = requests.post(f"{API}/pre-recorded", json=body, headers=HDR).json()
result_url = r["result_url"]

# 2. poll
while True:
    res = requests.get(result_url, headers={"x-gladia-key": KEY}).json()
    if res["status"] == "done":
        print(res["result"]["transcription"]["full_transcript"])
        break
    if res["status"] == "error":
        raise RuntimeError(res)
    time.sleep(2)

# submit a job
curl --request POST \
  --url 'https://api.gladia.io/v2/pre-recorded' \
  --header "x-gladia-key: $GLADIA_API_KEY" \
  --header 'Content-Type: application/json' \
  --data '{
    "audio_url": "https://files.gladia.io/example/audio-transcription/split_infinity.wav",
    "diarization": true,
    "subtitles": true,
    "subtitles_config": {"formats": ["srt"]}
  }'
# response includes { id, result_url }

# poll until status=done
curl --request GET \
  --url "$RESULT_URL" \
  --header "x-gladia-key: $GLADIA_API_KEY"

// npm i ws node-fetch
import fetch from "node-fetch";
import WebSocket from "ws";

const KEY = process.env.GLADIA_API_KEY;

// 1. init session
const init = await fetch("https://api.gladia.io/v2/live", {
  method: "POST",
  headers: {
    "x-gladia-key": KEY,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    encoding: "wav/pcm",
    sample_rate: 16000,
    bit_depth: 16,
    channels: 1,
  }),
}).then((r) => r.json());

// 2. open the WebSocket
const ws = new WebSocket(init.url);

ws.on("open", () => {
  // send 16 kHz / 16-bit PCM frames here
});

ws.on("message", (msg) => {
  const evt = JSON.parse(msg.toString());
  if (evt.type === "transcript" && evt.data?.is_final) {
    console.log(evt.data.utterance.text);
  }
});