提出音訊轉錄要求 (Beta 版)

同步轉錄本機音訊檔案。

程式碼範例

Python

如要瞭解如何安裝及使用 Speech-to-Text 的用戶端程式庫，請參閱這篇文章。 詳情請參閱 Speech-to-Text Python API 參考說明文件。

如要向語音轉文字服務進行驗證，請設定應用程式預設憑證。 詳情請參閱「為本機開發環境設定驗證」。

from google.cloud import speech_v1p1beta1 as speech


def sample_recognize(storage_uri: str) -> speech.RecognizeResponse:
    """
    Performs synchronous speech recognition on an audio file

    Args:
      storage_uri URI for audio file in Cloud Storage, e.g. gs://[BUCKET]/[FILE]
    """

    client = speech.SpeechClient()

    # storage_uri = 'gs://cloud-samples-data/speech/brooklyn_bridge.mp3'

    # The language of the supplied audio
    language_code = "en-US"

    # Sample rate in Hertz of the audio data sent
    sample_rate_hertz = 44100

    # Encoding of audio data sent. This sample sets this explicitly.
    # This field is optional for FLAC and WAV audio formats.
    encoding = speech.RecognitionConfig.AudioEncoding.MP3
    config = {
        "language_code": language_code,
        "sample_rate_hertz": sample_rate_hertz,
        "encoding": encoding,
    }
    audio = {"uri": storage_uri}

    response = client.recognize(config=config, audio=audio)

    for result in response.results:
        # First alternative is the most probable result
        alternative = result.alternatives[0]
        print(f"Transcript: {alternative.transcript}")

後續步驟

如要搜尋及篩選其他 Google Cloud 產品的程式碼範例，請參閱Google Cloud 範例瀏覽器。