Live translation

# pip install "websockets>=14"
import asyncio, base64, json, websockets

URL = (
    "wss://api.eesi.ai/v1/realtime/translations"
    "?model=nur-realtime-v1&language=es&source_language=en"
)

async def interpret(pcm_chunks):
    async with websockets.connect(
        URL, additional_headers={"Authorization": "Bearer sk-eesi-..."}
    ) as ws:
        # eesi.synthetic_audio, eesi.recording_disclosure, eesi.session,
        # then session.created. The loop below reads every type it needs, so
        # nothing here has to count frames.

        async def send():
            for chunk in pcm_chunks:          # 16 kHz mono PCM16, ~100 ms each
                await ws.send(json.dumps({
                    "type": "input_audio_buffer.append",
                    "audio": base64.b64encode(chunk).decode(),
                }))
                await asyncio.sleep(0.1)      # pace it — VAD reads arrival timing

        asyncio.create_task(send())
        async for raw in ws:
            event = json.loads(raw)
            if event["type"] == "response.output_audio_transcript.delta":
                print(event["delta"], end="", flush=True)
            elif event["type"] == "response.output_audio.delta":
                speaker.write(base64.b64decode(event["delta"]))

// npm install ws
import WebSocket from "ws";

const ws = new WebSocket(
  "wss://api.eesi.ai/v1/realtime/translations" +
    "?model=nur-realtime-v1&language=es&source_language=en",
  { headers: { Authorization: `Bearer ${process.env.EESI_API_KEY}` } },
);

ws.on("message", (raw) => {
  const event = JSON.parse(raw.toString());
  if (event.type === "response.output_audio.delta") {
    speaker.write(Buffer.from(event.delta, "base64"));
  }
});

// Mint a ticket on your server first — same call as a Live session.
const ws = new WebSocket(
  "wss://api.eesi.ai/v1/realtime/translations" +
    `?model=nur-realtime-v1&language=es&token=${ticket}`,
);