Google Cloud Speech API Python Samples

This directory contains samples for Google Cloud Speech API. The Google Cloud Speech API enables easy integration of Google speech recognition technologies into developer applications. Send audio and receive a text transcription from the Cloud Speech API service.

• See the migration guide for information about migrating to Python client library v0.27.

Setup

Authentication

Authentication is typically done through Application Default Credentials, which means you do not have to change the code to authenticate as long as your environment has credentials. You have a few options for setting up authentication:

1. When running locally, use the Google Cloud SDK

   gcloud auth application-default login

2. When running on App Engine or Compute Engine, credentials are already set-up. However, you may need to configure your Compute Engine instance with additional scopes.

3. You can create a Service Account key file. This file can be used to authenticate to Google Cloud Platform services from any environment. To use the file, set the GOOGLE_APPLICATION_CREDENTIALS environment variable to the path to the key file, for example:

   export GOOGLE_APPLICATION_CREDENTIALS=/path/to/service_account.json

Install Dependencies

1. Install pip and virtualenv if you do not already have them.

2. Create a virtualenv. Samples are compatible with Python 2.7 and 3.4+.

   $ virtualenv env
   $ source env/bin/activate

3. Install the dependencies needed to run the samples.

   $ pip install -r requirements.txt

Samples

Quickstart

To run this sample:

$ python quickstart.py

Transcribe

To run this sample:

$ python transcribe.py

usage: transcribe.py [-h] path

Google Cloud Speech API sample application using the REST API for batch
processing.

Example usage:
    python transcribe.py resources/audio.raw
    python transcribe.py gs://cloud-samples-tests/speech/brooklyn.flac

positional arguments:
  path        File or GCS path for audio file to be recognized

optional arguments:
  -h, --help  show this help message and exit

Transcribe async

To run this sample:

$ python transcribe_async.py

usage: transcribe_async.py [-h] path

Google Cloud Speech API sample application using the REST API for async
batch processing.

Example usage:
    python transcribe_async.py resources/audio.raw
    python transcribe_async.py gs://cloud-samples-tests/speech/vr.flac

positional arguments:
  path        File or GCS path for audio file to be recognized

optional arguments:
  -h, --help  show this help message and exit

Transcribe with word time offsets

To run this sample:

$ python transcribe_word_time_offsets.py

usage: transcribe_word_time_offsets.py [-h] path

Google Cloud Speech API sample that demonstrates word time offsets.

Example usage:
    python transcribe_word_time_offsets.py resources/audio.raw
    python transcribe_word_time_offsets.py         gs://cloud-samples-tests/speech/vr.flac

positional arguments:
  path        File or GCS path for audio file to be recognized

optional arguments:
  -h, --help  show this help message and exit

Transcribe Streaming

To run this sample:

$ python transcribe_streaming.py

usage: transcribe_streaming.py [-h] stream

Google Cloud Speech API sample application using the streaming API.

Example usage:
    python transcribe_streaming.py resources/audio.raw

positional arguments:
  stream      File to stream to the API

optional arguments:
  -h, --help  show this help message and exit

The client library

This sample uses the Google Cloud Client Library for Python. You can read the documentation for more details on API usage and use GitHub to browse the source and report issues.