Live Translation

import WebSocket from 'ws'
import fs from 'node:fs'

const KEY = process.env.LOKUTOR_API_KEY
const wav = fs.readFileSync('speech_es_16k.wav')
const pcm = wav.subarray(44) // assumes a plain 44-byte header, PCM16 mono 16 kHz
const OUT_RATE = 44100

const ws = new WebSocket('wss://api.lokutor.com/v1/ws/translate', { headers: { 'X-API-Key': KEY } })
const audio = []

ws.on('open', () => ws.send(JSON.stringify({
  type: 'config', source_language: 'es', target_language: 'en',
  voice: 'en_f1', input_rate: 16000, output_rate: OUT_RATE,
})))

ws.on('message', async (data, isBinary) => {
  if (isBinary) { audio.push(data); return }
  const m = JSON.parse(data.toString())
  if (m.type === 'ready') {
    const frame = 16000 * 2 * 0.02 // 20 ms of PCM16
    for (let i = 0; i < pcm.length; i += frame) {
      ws.send(pcm.subarray(i, i + frame))
      await new Promise(r => setTimeout(r, 20)) // real-time pace
    }
    ws.send(JSON.stringify({ type: 'end' }))
  } else if (m.type === 'transcript' && m.final) console.log('heard:', m.text)
  else if (m.type === 'translation' && m.final) console.log('said :', m.text)
  else if (m.type === 'error') console.error(m.data)
  else if (m.type === 'end') {
    const body = Buffer.concat(audio)
    const h = Buffer.alloc(44)
    h.write('RIFF', 0); h.writeUInt32LE(36 + body.length, 4); h.write('WAVEfmt ', 8)
    h.writeUInt32LE(16, 16); h.writeUInt16LE(1, 20); h.writeUInt16LE(1, 22)
    h.writeUInt32LE(OUT_RATE, 24); h.writeUInt32LE(OUT_RATE * 2, 28)
    h.writeUInt16LE(2, 32); h.writeUInt16LE(16, 34); h.write('data', 36); h.writeUInt32LE(body.length, 40)
    fs.writeFileSync('translated.wav', Buffer.concat([h, body]))
    ws.close()
  }
})

import asyncio, json, os, wave
import websockets

KEY = os.environ["LOKUTOR_API_KEY"]
OUT_RATE = 44100

async def main():
    with wave.open("speech_es_16k.wav", "rb") as w:   # PCM16 mono 16 kHz
        pcm = w.readframes(w.getnframes())
    frame = 16000 * 2 * 20 // 1000                    # 20 ms of PCM16
    audio = bytearray()

    # websockets >= 14 uses additional_headers; older versions use extra_headers
    async with websockets.connect("wss://api.lokutor.com/v1/ws/translate",
                                  additional_headers={"X-API-Key": KEY}) as ws:
        await ws.send(json.dumps({"type": "config", "source_language": "es", "target_language": "en",
                                  "voice": "en_f1", "input_rate": 16000, "output_rate": OUT_RATE}))
        assert json.loads(await ws.recv())["type"] == "ready"

        async def send_file():
            for i in range(0, len(pcm), frame):
                await ws.send(pcm[i:i + frame])
                await asyncio.sleep(0.02)             # real-time pace
            await ws.send(json.dumps({"type": "end"}))

        sender = asyncio.create_task(send_file())
        async for msg in ws:
            if isinstance(msg, bytes):
                audio += msg
                continue
            m = json.loads(msg)
            if m["type"] == "transcript" and m["final"]:
                print("heard:", m["text"])
            elif m["type"] == "translation" and m["final"]:
                print("said :", m["text"])
            elif m["type"] == "error":
                print("error:", m["data"])
            elif m["type"] == "end":
                break
        await sender

    with wave.open("translated.wav", "wb") as out:
        out.setnchannels(1); out.setsampwidth(2); out.setframerate(OUT_RATE)
        out.writeframes(bytes(audio))

asyncio.run(main())