JavaScript وTypeScript

npm install @humain-voice/sdk@0.18.0

export API_URL="https://api.voice.humain.com"
export API_KEY="YOUR_API_KEY"
export API_VERSION="v1"

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 {
  FastTranscriptionClient,
  FastTranscriptionModel,
  Language,
  Subtitles,
} from '@humain-voice/sdk';

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 withDeadline<T>(operation: Promise<T>, milliseconds: number): Promise<T> {
  let timer: ReturnType<typeof setTimeout> | undefined;
  try {
    return await Promise.race([
      operation,
      new Promise<never>((_, reject) => {
        timer = setTimeout(() => reject(new Error('Fast transcription deadline exceeded')), milliseconds);
      }),
    ]);
  } finally {
    if (timer) clearTimeout(timer);
  }
}

async function main(): Promise<void> {
  const inputPath = process.argv[2] ?? 'short-call.wav';
  const outputPath = process.argv[3] ?? 'short-call.srt';
  const client = new FastTranscriptionClient({
    api_url: requiredEnv('API_URL'),
    api_path: requiredEnv('API_PATH'),
    api_key: requiredEnv('API_KEY'),
  });

  try {
    await client.connect();
    const result = await withDeadline(
      client.transcribe(
        await readFile(inputPath),
        Language.Ar,
        FastTranscriptionModel.BayanAr,
        {
          onFileUpload: (response) => console.info('uploaded:', response?.id),
          onResponse: (response) => {
            console.info(response.is_final ? 'final:' : 'partial:', response.transcription);
          },
          onError: (error) => console.error('server error:', error.code, error.message),
        },
      ),
      60_000,
    );

    if (!result) throw new Error('Fast transcription ended without a final result');
    await writeFile(outputPath, Subtitles.fromResponse(result).toSrt(), '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;
});

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

import {
  DIARIZATION_RECOMMENDED_CHUNK_BYTES,
  RealtimeDiarizationClient,
  type SpeakerSegment,
  toRttm,
} from '@humain-voice/sdk';

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] ?? 'meeting.pcm';
  const outputPath = process.argv[3] ?? 'meeting.rttm';
  const client = new RealtimeDiarizationClient({
    api_url: requiredEnv('API_URL'),
    api_path: requiredEnv('API_PATH'),
    api_key: requiredEnv('API_KEY'),
  });

  try {
    let finalObserved = false;
    const stream = await client.startStream({
      onError: (error) => console.error('server error:', error.code, error.message),
      onUpdate: (update) => {
        finalObserved ||= update.isFinal;
        for (const segment of update.newlyFinalized) {
          console.info(segment.speaker, segment.start_time, segment.end_time);
        }
      },
    });
    const pcm = await readFile(inputPath);

    if (pcm.length === 0 || pcm.length % 2 !== 0) {
      throw new Error('Input must be nonempty PCM16 with an even byte length');
    }
    for (
      let offset = 0;
      offset < pcm.length;
      offset += DIARIZATION_RECOMMENDED_CHUNK_BYTES
    ) {
      await stream.send(
        pcm.subarray(offset, offset + DIARIZATION_RECOMMENDED_CHUNK_BYTES),
      );
      await pause(480);
    }

    // close() returns the best-known reconciled timeline after five seconds,
    // even when no isFinal update arrived. A callback avoids leaving an async
    // iterator waiting forever on that timeout path.
    const timeline: SpeakerSegment[] = await stream.close(5);
    const destination = finalObserved ? outputPath : `${outputPath}.partial`;
    await writeFile(destination, toRttm(timeline, 'meeting'), 'utf8');
    if (!finalObserved) {
      console.warn(`Final result not observed; wrote incomplete output to ${destination}`);
    }
  } finally {
    await client.disconnect();
  }
}

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

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

import {
  TTSClient,
  TtsModel,
  getSampleRate,
} from '@humain-voice/sdk';

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;
}

function pcm16ToWav(pcm: Uint8Array, sampleRate: number): Buffer {
  const header = Buffer.alloc(44);
  header.write('RIFF', 0);
  header.writeUInt32LE(36 + pcm.byteLength, 4);
  header.write('WAVE', 8);
  header.write('fmt ', 12);
  header.writeUInt32LE(16, 16);
  header.writeUInt16LE(1, 20); // Linear PCM.
  header.writeUInt16LE(1, 22); // Mono.
  header.writeUInt32LE(sampleRate, 24);
  header.writeUInt32LE(sampleRate * 2, 28);
  header.writeUInt16LE(2, 32);
  header.writeUInt16LE(16, 34);
  header.write('data', 36);
  header.writeUInt32LE(pcm.byteLength, 40);

  return Buffer.concat([
    header,
    Buffer.from(pcm.buffer, pcm.byteOffset, pcm.byteLength),
  ]);
}

async function main(): Promise<void> {
  const outputPath = process.argv[2] ?? 'speech.wav';
  const client = new TTSClient({
    api_url: requiredEnv('API_URL'),
    api_path: requiredEnv('API_PATH'),
    api_key: requiredEnv('API_KEY'),
  });

  try {
    const voices = await client.listVoices({ timeoutSeconds: 5 });
    const voice = voices.find((candidate) => candidate.profile) ?? voices[0];
    if (!voice) throw new Error('No TTS voices are available');
    if (voice.profile) {
      console.log(
        'profile:',
        voice.label,
        voice.profile.speaker.dialect,
        voice.profile.languages,
      );
    }

    const model = TtsModel.Nebula;
    const pcm = await client.synthesize('Hello from HUMAIN Voice', {
      voice_id: voice.id,
      model,
      // This is an inactivity timeout applied while awaiting each audio chunk.
      timeoutSeconds: 30,
      onError: (error) => console.error('server error:', error.code, error.message),
    });

    await writeFile(outputPath, pcm16ToWav(pcm, getSampleRate(model)));
  } finally {
    await client.close();
  }
}

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

import {
  BatchTranscribeClient,
  BatchTranscribeError,
  BatchTranscribeRateLimitError,
  Language,
  type TranscriptionResponse,
} 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 pause(milliseconds: number): Promise<void> {
  await new Promise<void>((resolve) => setTimeout(resolve, milliseconds));
}

async function getResultWithRetry(
  client: BatchTranscribeClient,
  jobId: string,
  attempts = 5,
): Promise<TranscriptionResponse> {
  for (let attempt = 1; attempt <= attempts; attempt += 1) {
    try {
      // saveResult prevents a terminal read from clearing the stored result
      // before a retry. It does not establish a retention duration.
      return await client.getResult(jobId, Language.ArEn, { saveResult: true });
    } catch (error: unknown) {
      if (!(error instanceof BatchTranscribeError)) throw error;

      const rateLimited = error instanceof BatchTranscribeRateLimitError;
      const retryable = rateLimited || error.retryable === true;
      console.error({
        statusCode: error.statusCode,
        code: error.code,
        capacity: error.capacity,
      });
      if (!retryable || attempt === attempts) throw error;

      const serverDelayMs = rateLimited && error.retryAfter !== undefined
        ? error.retryAfter * 1_000
        : 0;
      const exponentialDelayMs = 500 * 2 ** (attempt - 1);
      await pause(Math.max(serverDelayMs, exponentialDelayMs) + Math.random() * 250);
    }
  }

  throw new Error('Retry loop exhausted');
}

async function main(): Promise<void> {
  const jobId = process.argv[2];
  if (!jobId) throw new Error('Pass a batch job ID as the first argument');

  const client = new BatchTranscribeClient({
    api_url: requiredEnv('API_URL'),
    api_key: requiredEnv('API_KEY'),
  });
  try {
    const result = await getResultWithRetry(client, jobId);
    console.info(result.status, result.results?.transcript ?? '');
  } finally {
    await client.close();
  }
}

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