البدء السريع

import { readFile, writeFile } from 'node:fs/promises';

import {
  BatchDiarization,
  BatchTranscribeClient,
  BatchTranscriptionModel,
  Language,
  Subtitles,
} from '@humain-voice/sdk';

function requiredEnv(name: 'API_KEY' | 'API_URL'): string {
  const value = process.env[name];
  if (!value) throw new Error(`${name} is required`);
  return value;
}

async function main(): Promise<void> {
  const inputPath = process.argv[2] ?? 'meeting.wav';
  const outputPath = process.argv[3] ?? 'meeting.vtt';
  const client = new BatchTranscribeClient({
    api_url: requiredEnv('API_URL'),
    api_key: requiredEnv('API_KEY'),
    api_version: process.env.API_VERSION ?? 'v1',
  });

  try {
    const result = await client.transcribe(
      await readFile(inputPath),
      Language.ArEn,
      {
        asr: BatchTranscriptionModel.BayanArEn,
        diarization: BatchDiarization.On,
        saveResult: true,
        pollInterval: 2,
        timeout: 300,
        onProgress: ({ status }) => console.info('status:', status),
      },
    );

    console.info(result.results?.transcript ?? '');
    await writeFile(outputPath, Subtitles.fromResponse(result).toVtt(), 'utf8');
  } finally {
    await client.close();
  }
}

void main().catch((error: unknown) => {
  console.error(error);
  process.exitCode = 1;
});

import { readFile, writeFile } from 'node:fs/promises';

import {
  type ErrorResponse,
  Language,
  RealtimeClient,
  Subtitles,
  type WordSegment,
} from '@humain-voice/sdk';

const CHUNK_BYTES = 3_200; // 100 ms of PCM16LE, 16 kHz, mono audio.

function requiredEnv(name: 'API_KEY' | 'API_PATH' | 'API_URL'): string {
  const value = process.env[name];
  if (!value) throw new Error(`${name} is required`);
  return value;
}

async function pause(milliseconds: number): Promise<void> {
  await new Promise<void>((resolve) => setTimeout(resolve, milliseconds));
}

async function main(): Promise<void> {
  const inputPath = process.argv[2] ?? 'speech.pcm';
  const outputPath = process.argv[3] ?? 'speech.vtt';
  const client = new RealtimeClient({
    api_url: requiredEnv('API_URL'),
    api_path: requiredEnv('API_PATH'),
    api_key: requiredEnv('API_KEY'),
  });
  const finalizedWords: WordSegment[] = [];
  let serverError: ErrorResponse | undefined;
  let protocolFinalObserved = false;

  try {
    const stream = await client.startStream(Language.ArEn, {
      onResponse: (response) => {
        const kind = response.is_final
          ? 'final'
          : response.is_speech_final
            ? 'speech-final'
            : 'partial';
        console.info(`${kind}:`, response.transcription);
        if (response.is_final) protocolFinalObserved = true;
        if (response.is_final || response.is_speech_final) {
          // The current public Realtime contract does not guarantee increasing
          // seq values, so collect final words in arrival order instead of
          // asking RealtimeSubtitles to deduplicate by id:seq.
          finalizedWords.push(...response.words);
        }
      },
      // The released SDK can invoke a stream handler more than once for one
      // routed error, so keep this callback idempotent.
      onError: (error) => {
        serverError = error;
      },
    });

    const pcm = await readFile(inputPath);
    for (let offset = 0; offset < pcm.length; offset += CHUNK_BYTES) {
      await stream.send(pcm.subarray(offset, offset + CHUNK_BYTES));
      await pause(100);
    }

    // close() sends the last frame and waits for protocol is_final, a routed
    // error, or this timeout. It resolves rather than throwing on timeout.
    await stream.close(5);
    if (serverError) {
      throw new Error(serverError.message ?? serverError.code ?? 'Realtime stream failed');
    }
    if (!protocolFinalObserved) {
      throw new Error('Realtime stream ended before protocol is_final');
    }
    await writeFile(outputPath, Subtitles.fromWords(finalizedWords).toVtt(), 'utf8');
  } finally {
    await client.disconnect();
  }
}

void main().catch((error: unknown) => {
  console.error(error);
  process.exitCode = 1;
});