google-cloud-speech

Google Cloud Speech API client library

google-cloud-speech Permissive license Apache-2.0 Active ★ 5,370 v2.40.0 released 2026-06-03

Install

google-cloud-speech on PyPI

pip

pip install google-cloud-speech

uv

uv add google-cloud-speech

poetry

poetry add google-cloud-speech

Package facts

License	Apache-2.0 (permissive)
Python support	supports the current Python release (>=3.10)
Install friction	low — pure-Python wheel
Runtime dependencies	5 — google-api-core, google-auth, grpcio, proto-plus, protobuf
Maintenance	actively maintained — 71 days since the last release
Last repo commit	2026-08-13
First released	2016-11-14
Popularity	one of the top 1,000 most-downloaded packages on PyPI (30-day window, as of 2026-08-13)
Known vulnerabilities	none known (OSV.dev, checked 2026-08-13)

Evidence: google_cloud_speech-2.40.0-py3-none-any.whl

Development Status :: 5 - Production/StableIntended Audience :: DevelopersLicense :: OSI Approved :: Apache Software LicenseOperating System :: OS IndependentProgramming Language :: PythonProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14Topic :: Internet

About google-cloud-speech

from the package's own PyPI description — quoted content, verbatim

Python Client for Cloud Speech-to-Text

Cloud Speech-to-Text_: Converts audio to text by applying powerful neural network models.

Client Library Documentation_
Product Documentation_

.. |stable| image:: https://img.shields.io/badge/support-stable-gold.svg :target: https://github.com/googleapis/google-cloud-python/blob/main/README.rst#stability-levels .. |pypi| image:: https://img.shields.io/pypi/v/google-cloud-speech.svg :target: https://pypi.org/project/google-cloud-speech/ .. |versions| image:: https://img.shields.io/pypi/pyversions/google-cloud-speech.svg :target: https://pypi.org/project/google-cloud-speech/ .. _Cloud Speech-to-Text: https://cloud.google.com/speech-to-text/ .. _Client Library Documentation: https://cloud.google.com/python/docs/reference/speech/latest/summary_overview .. _Product Documentation: https://cloud.google.com/speech-to-text/

Quick Start

In order to use this library, you first need to go through the following steps:

Select or create a Cloud Platform project._
Enable billing for your project._
Enable the Cloud Speech-to-Text._ 4....

Read as markdown · JSON record · Source repository · Homepage

AI interpretation — verify before relying

AI-generated interpretation of the package facts above; every digit, version, license, or vulnerability id it cites is grounded in the facts already shown on this page

Python client library for Google Cloud Speech-to-Text that converts audio to text using neural network models via the Google Cloud API.

Low friction install with a pure-wheel distribution. Active maintenance with recent releases (71 days since last update) and a well-established codebase (since 2016). Requires Python 3.10+.

Licensed under Apache-2.0 (permissive), allowing commercial use, modification, and distribution with minimal restrictions.

Usage

pip install google-cloud-speech

from google.cloud import speech_v1

client = speech_v1.SpeechClient()
config = speech_v1.RecognitionConfig(language_code="en-US")
audio = speech_v1.RecognitionAudio(uri="gs://bucket/audio.wav")
response = client.recognize(config=config, audio=audio)

Requires Google Cloud project with Speech-to-Text API enabled and authentication credentials configured (via GOOGLE_APPLICATION_CREDENTIALS or similar).

Verdict: Stable, actively maintained Google-backed library with no known vulnerabilities and low install friction. Suitable for production use, though requires Google Cloud setup and authentication. Apache-2.0 license poses no restrictions for most use cases.

Needs verification

Whether the library handles audio streaming or only batch requests
Pricing implications and quota limits for the underlying Cloud Speech-to-Text service
Performance characteristics and latency expectations for typical workloads

speech to text apiaudio transcription google cloudspeech recognition pythongoogle cloud speech clientaudio to text conversionneural network speech recognitioncloud speech api python