README.rst

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

This sample requires you to have authentication setup. Refer to the Authentication Getting Started Guide for instructions on setting up credentials for applications.

Install Dependencies

1. Clone python-docs-samples and change directory to the sample directory you want to use.

   $ git clone https://github.com/googleapis/python-speech.git 

2. Install pip and virtualenv if you do not already have them. You may want to refer to the Python Development Environment Setup Guide for Google Cloud Platform for instructions.

   https://cloud.google.com/python/setup

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

   $ virtualenv env
   $ source env/bin/activate

4. 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

Transcribe Enhanced Models

To run this sample:

$ python transcribe_enhanced_model.py

usage: transcribe_enhanced_model.py [-h] path

Google Cloud Speech API sample that demonstrates enhanced models
and recognition metadata.

Example usage:
    python transcribe_enhanced_model.py resources/commercial_mono.wav

positional arguments:
  path        File to stream to the API

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

Transcribe Automatic Punctuation

To run this sample:

$ python transcribe_auto_punctuation.py

usage: transcribe_auto_punctuation.py [-h] path

Google Cloud Speech API sample that demonstrates auto punctuation
and recognition metadata.

Example usage:
    python transcribe_auto_punctuation.py resources/commercial_mono.wav

positional arguments:
  path        File to stream to the API

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

Transcribe with Model Selection

To run this sample:

$ python transcribe_model_selection.py

  usage: transcribe_model_selection.py [-h]
                                       [--model {command_and_search,phone_call,video,default}]
                                       path

  Google Cloud Speech API sample that demonstrates how to select the model
  used for speech recognition.

  Example usage:
      python transcribe_model_selection.py resources/Google_Gnome.wav --model video
      python transcribe_model_selection.py gs://cloud-samples-tests/speech/Google_Gnome.wav --model video

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

  optional arguments:
    -h, --help            show this help message and exit
    --model {command_and_search,phone_call,video,default}
                          The speech recognition model to use

Beta Samples

To run this sample:

$ python beta_snippets.py

usage: beta_snippets.py [-h] command

Google Cloud Speech API sample that demonstrates enhanced models
and recognition metadata.

Example usage:
    python beta_snippets.py enhanced-model
    python beta_snippets.py metadata
    python beta_snippets.py punctuation
    python beta_snippets.py diarization
    python beta_snippets.py multi-channel
    python beta_snippets.py multi-language
    python beta_snippets.py word-level-conf

positional arguments:
  command

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.