实时转录

import { createReadStream } from 'node:fs';
import { setTimeout as sleep } from 'node:timers/promises';
import { Transcript1 } from '@transcript1/sdk';
 
const t1 = new Transcript1(); // reads TRANSCRIPT1_API_KEY
 
const live = await t1.live.start({ language: 'en', translateTo: 'es', sampleRate: 16000 });
 
live.on('line', line => {
  const mark = line.final ? 'final  ' : 'partial';
  console.log(mark, line.text, '→', line.translation?.text ?? '');
});
live.on('warning', warning => console.warn(warning.code));
 
// speech.pcm: 16 kHz, mono, signed 16-bit little-endian, no header
for await (const chunk of createReadStream('./speech.pcm', { highWaterMark: 3200 })) {
  live.send(chunk);
  await sleep(100); // 3,200 bytes are 100 ms of audio: send at real-time speed
}
 
const result = await live.end();
console.log(result.reason, result.transcriptionId, result.minutesCharged);

curl -X POST https://api.transcript1.com/v1/live/sessions \
  -H "Authorization: Bearer $TRANSCRIPT1_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"language": "en", "translate_to": "es", "sample_rate": 16000}'

{
  "id": "lv_8fK2Lm0PqRsTuVwXyZaBcD",
  "status": "waiting",
  "transcription_id": "tr_3NcQvXy7BtHjKd5ErFgLmA",
  "websocket_url": "wss://api.transcript1.com/v1/live/sessions/lv_8fK2Lm0PqRsTuVwXyZaBcD/stream",
  "token": "Zk3x...",
  "token_expires_at": "2026-11-02T12:01:00Z",
  "rate": 1
}

import { createReadStream } from 'node:fs';
import { setTimeout as sleep } from 'node:timers/promises';
 
const session = await fetch('https://api.transcript1.com/v1/live/sessions', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.TRANSCRIPT1_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({ language: 'en', translate_to: 'es', sample_rate: 16000 }),
}).then(response => response.json());
 
const ws = new WebSocket(session.websocket_url, ['t1-live', session.token]);
const lines = new Map();
 
ws.addEventListener('message', async message => {
  const event = JSON.parse(message.data);
 
  if (event.type === 'session.started') {
    for await (const chunk of createReadStream('./speech.pcm', { highWaterMark: 3200 })) {
      ws.send(chunk);
      await sleep(100);
    }
    ws.send(JSON.stringify({ type: 'end' }));
  } else if (event.type === 'line') {
    lines.set(event.line.id, event.line); // the full current state: replace by id
    console.log(event.line.final, event.line.text, event.line.translation?.text);
  } else if (event.type === 'session.ended') {
    console.log('ended:', event.reason, event.minutes_charged);
  }
});
 
ws.addEventListener('close', event => console.log('closed', event.code));

import { createLiveClient } from '@transcript1/sdk/live';
 
const workletSource = `
class Pcm16Processor extends AudioWorkletProcessor {
  constructor() {
    super();
    this.buffer = new Int16Array(1600); // 100 ms at 16 kHz
    this.filled = 0;
  }
 
  process(inputs) {
    const channel = inputs[0][0];
    if (!channel) return true;
    for (let i = 0; i < channel.length; i++) {
      const sample = Math.max(-1, Math.min(1, channel[i]));
      this.buffer[this.filled++] = sample < 0 ? sample * 0x8000 : sample * 0x7fff;
      if (this.filled === this.buffer.length) {
        this.port.postMessage(this.buffer.slice());
        this.filled = 0;
      }
    }
    return true;
  }
}
registerProcessor('pcm16', Pcm16Processor);
`;
 
const client = createLiveClient({ getAccessToken: () => myApp.getOAuthAccessToken() });
 
const stream = await navigator.mediaDevices.getUserMedia({ audio: { channelCount: 1 } });
const context = new AudioContext({ sampleRate: 16000 });
const moduleUrl = URL.createObjectURL(new Blob([workletSource], { type: 'text/javascript' }));
await context.audioWorklet.addModule(moduleUrl);
 
// the context's real rate: a browser that cannot do 16 kHz picks its own
const live = await client.start({ language: 'auto', sampleRate: context.sampleRate });
live.on('line', renderLine);
 
const microphone = context.createMediaStreamSource(stream);
const capture = new AudioWorkletNode(context, 'pcm16');
capture.port.onmessage = event => live.send(event.data); // an Int16Array
const mute = context.createGain();
mute.gain.value = 0;
microphone.connect(capture).connect(mute).connect(context.destination);
 
async function stop() {
  stream.getTracks().forEach(track => track.stop());
  await context.close();
  return live.end();
}

new WebSocket(websocket_url, ['t1-live', token]);

{
  "type": "session.started",
  "session_id": "lv_8fK2Lm0PqRsTuVwXyZaBcD",
  "transcription_id": "tr_3NcQvXy7BtHjKd5ErFgLmA",
  "resumed": false,
  "offset_ms": 0
}

{
  "type": "line",
  "line": {
    "id": 12,
    "start_ms": 53120,
    "end_ms": 56040,
    "speaker": null,
    "language": "en",
    "text": "Welcome back to the stream",
    "final": true,
    "translation": { "language": "es", "text": "Bienvenidos de nuevo", "final": false }
  }
}

{
  "type": "usage",
  "connected_ms": 61240,
  "audio_ms": 60100,
  "minutes_charged": 2,
  "minutes_remaining": 898
}

{ "type": "warning", "code": "idle_timeout_soon" }

{ "type": "error", "code": "invalid_message", "message": "Expected {\"type\":\"finalize\"} or {\"type\":\"end\"}" }

{ "type": "reconnect", "reason": "server_restart" }

{
  "type": "session.ended",
  "reason": "client_ended",
  "transcription_id": "tr_3NcQvXy7BtHjKd5ErFgLmA",
  "minutes_charged": 3,
  "connected_ms": 142500,
  "audio_ms": 141900
}

{
  "available": true,
  "auto_language": true,
  "languages": ["en", "es"],
  "translation": {
    "targets": ["es", "de"],
    "pairs": "any",
    "requires_language": false
  },
  "diarize": true,
  "audio_formats": ["pcm_s16le"],
  "sample_rate": { "min": 8000, "max": 48000 },
  "max_session_minutes": 300,
  "rate": 1
}

curl https://api.transcript1.com/v1/live/sessions/lv_8fK2Lm0PqRsTuVwXyZaBcD \
  -H "Authorization: Bearer $TRANSCRIPT1_API_KEY"

{
  "id": "lv_8fK2Lm0PqRsTuVwXyZaBcD",
  "status": "ended",
  "end_reason": "client_ended",
  "transcription_id": "tr_3NcQvXy7BtHjKd5ErFgLmA",
  "options": {
    "language": "en",
    "translate_to": "es",
    "diarize": false,
    "audio_format": "pcm_s16le",
    "sample_rate": 16000,
    "save": true
  },
  "connected_ms": 142500,
  "audio_ms": 141900,
  "minutes_charged": 3,
  "rate": 1,
  "created_at": "2026-11-02T11:58:12Z",
  "ended_at": "2026-11-02T12:00:35Z"
}