Speech-to-text WebSocket examples

// npm install ws
const WebSocket = require("ws");
const fs = require("fs");

const API_KEY = process.env.SLNG_API_KEY;
const AUDIO_FILE = process.argv[2] || "input.wav";

const ws = new WebSocket("wss://api.slng.ai/v1/stt/slng/deepgram/nova:3-en", {
  headers: { Authorization: `Bearer ${API_KEY}` },
});

ws.on("open", () => {
  // 1. Initialize session
  ws.send(
    JSON.stringify({
      type: "init",
      config: {
        language: "en",
        sample_rate: 16000,
        encoding: "linear16",
      },
    }),
  );
});

ws.on("message", (data) => {
  const message = JSON.parse(data.toString());

  if (message.type === "ready") {
    console.log("Session ready:", message.session_id);

    // 2. Read and stream audio file in chunks
    const audio = fs.readFileSync(AUDIO_FILE);
    const CHUNK_SIZE = 4096;
    for (let i = 0; i < audio.length; i += CHUNK_SIZE) {
      ws.send(audio.slice(i, i + CHUNK_SIZE));
    }

    // 3. Signal end of audio
    ws.send(JSON.stringify({ type: "close" }));
  } else if (message.type === "partial_transcript") {
    console.log("Interim:", message.transcript);
  } else if (message.type === "final_transcript") {
    console.log("Final:", message.transcript);
  } else if (message.type === "error") {
    console.error("Error:", message.message);
    ws.close();
  }
});

ws.on("close", () => {
  console.log("Connection closed");
});

# pip install websockets
import asyncio
import json
import os
import sys
import websockets

CHUNK_SIZE = 4096

async def stt_quickstart():
    api_key = os.environ["SLNG_API_KEY"]
    audio_file = sys.argv[1] if len(sys.argv) > 1 else "input.wav"
    uri = "wss://api.slng.ai/v1/stt/slng/deepgram/nova:3-en"
    headers = {"Authorization": f"Bearer {api_key}"}

    async with websockets.connect(uri, extra_headers=headers) as ws:
        # 1. Initialize session
        await ws.send(json.dumps({
            "type": "init",
            "config": {
                "language": "en",
                "sample_rate": 16000,
                "encoding": "linear16",
            },
        }))

        # Wait for ready before streaming audio
        ready = json.loads(await ws.recv())
        print(f"Session ready: {ready['session_id']}")

        # 2. Read and stream audio file in chunks
        with open(audio_file, "rb") as f:
            while chunk := f.read(CHUNK_SIZE):
                await ws.send(chunk)

        # 3. Signal end of audio
        await ws.send(json.dumps({"type": "close"}))

        # 4. Receive transcription results
        async for message in ws:
            data = json.loads(message)
            if data["type"] == "partial_transcript":
                print(f"Interim: {data['transcript']}")
            elif data["type"] == "final_transcript":
                print(f"Final: {data['transcript']}")
            elif data["type"] == "error":
                print(f"Error: {data['message']}")
                break

asyncio.run(stt_quickstart())

node stt.js recording.wav

python stt.py recording.wav