Realtime STT (Manual)

const ws = new WebSocket(
  "wss://studio.evomlabs.com/api/public/v1/stt/ws" +
  "?token=stt_sk_live_YOUR_KEY&language=auto"
);

ws.addEventListener("open", () => {
  ws.send(JSON.stringify({
    type: "start",
    mode: "auto",
    language: "auto",
    sample_rate: 48000,
    format: "pcm_s16le",
  }));
});

ws.addEventListener("message", (event) => {
  const message = JSON.parse(event.data);
  if (message.type === "partial" || message.type === "segment") {
    renderTranscript(message.combined_text);
  }
  if (message.type === "final") {
    renderTranscript(message.text);
  }
  if (message.type === "error") {
    console.error(message.code, message.message);
  }
});

// Send PCM16 frames with ws.send(arrayBuffer).
function stopTranscription() {
  if (ws.readyState === WebSocket.OPEN) {
    ws.send(JSON.stringify({ type: "stop" }));
  }
}

// Start with: { "type": "start", "mode": "manual", ... }
// Send PCM16 frames, then commit exactly that buffered speech:
ws.send(JSON.stringify({ type: "commit" }));

// The server returns one final segment. Send commit again for the next turn,
// or stop to commit a sufficiently long trailing buffer and close the session.
ws.send(JSON.stringify({ type: "stop" }));