Google Cloud Text-to-Speech

2.35.0 · active · verified Thu Apr 09

The `google-cloud-texttospeech` client library for Python enables seamless integration with the Google Cloud Text-to-Speech API. It allows developers to convert text into natural-sounding speech using Google's advanced AI technologies, supporting a wide range of voices, languages, and customization options. As of version 2.35.0, it continues to be actively maintained with frequent updates as part of the broader Google Cloud Python client libraries.

Common errors

```
ModuleNotFoundError: No module named 'google.cloud'
```
cause This error occurs when the `google-cloud-texttospeech` library is not correctly installed in the Python environment, or if an old, deprecated `google-cloud` meta-package is installed instead of the specific client library.

fix Ensure you have the correct library installed by running: `pip install --upgrade google-cloud-texttospeech`. If you previously installed `google-cloud`, uninstall it with `pip uninstall google-cloud` first.
```
DefaultCredentialsError: Could not automatically determine credentials. Please set GOOGLE_APPLICATION_CREDENTIALS
```
cause The application cannot find the necessary Google Cloud credentials to authenticate with the Text-to-Speech API. This typically means the `GOOGLE_APPLICATION_CREDENTIALS` environment variable is not set or points to an invalid or non-existent service account key file.

fix Set the `GOOGLE_APPLICATION_CREDENTIALS` environment variable to the absolute path of your service account JSON key file. On Linux/macOS: `export GOOGLE_APPLICATION_CREDENTIALS="/path/to/your/key.json"`. On Windows (Command Prompt): `set GOOGLE_APPLICATION_CREDENTIALS="C:\path\to\your\key.json"`. Alternatively, use `gcloud auth application-default login` for local development.
```
AttributeError: module 'google.cloud.texttospeech' has no attribute 'types'
```
cause This error usually indicates a version incompatibility where the code is using an older syntax (e.g., `texttospeech.types.SynthesisInput`) that is no longer valid for the installed version of the `google-cloud-texttospeech` library, or vice-versa.

fix Update the `google-cloud-texttospeech` library to the latest version (`pip install --upgrade google-cloud-texttospeech`). If the error persists, check the official client library documentation for the correct way to import and use API types, as the structure might have changed (e.g., `texttospeech.SynthesisInput` directly instead of `texttospeech.types.SynthesisInput`).
```
Forbidden: 403 POST Cloud Text-to-Speech API has not been used in project # before or it is disabled.
```
cause The Google Cloud Text-to-Speech API is not enabled for the specific Google Cloud project being used, or the service account lacks the necessary permissions to access it.

fix Go to the Google Cloud Console, select your project, navigate to 'APIs & Services' > 'Enabled APIs & Services', and ensure that the 'Cloud Text-to-Speech API' is enabled. Also, verify that your service account has roles such as 'Cloud Text-to-Speech User' or a custom role with appropriate permissions.
```
RESOURCE_EXHAUSTED: Quota exceeded.
```
cause Your Google Cloud project has exceeded the allocated quota for the Text-to-Speech API, such as the number of characters synthesized per minute or total bytes per request.

fix Review your API usage in the Google Cloud Console ('IAM & Admin' > 'Quotas') for the Text-to-Speech API. You can request a quota increase if needed. For requests exceeding content limits, use asynchronous methods or process smaller chunks of text.

Warnings

breaking Google Cloud Text-to-Speech voices are periodically updated or replaced. Existing voice names in your application might be deprecated or behave differently, potentially causing unexpected audio output or errors.
Fix: Regularly check the Cloud Text-to-Speech release notes for voice updates. Consider using `client.list_voices()` to programmatically discover available voices and their names, and implement a fallback mechanism for voice selection. Test your application's voice output after significant service updates.
gotcha Incorrect authentication setup is a common issue. If `GOOGLE_APPLICATION_CREDENTIALS` is not set or Application Default Credentials (ADC) are not configured, the client will fail to connect to the API.
Fix: Ensure you have enabled the Text-to-Speech API in your Google Cloud project and set up authentication. For local development, use `gcloud auth application-default login` or set the `GOOGLE_APPLICATION_CREDENTIALS` environment variable to the path of your service account key file. For production, refer to the ADC documentation.
gotcha Using an invalid `language_code`, `name`, or `ssml_gender` in `VoiceSelectionParams` can lead to `InvalidArgument` errors.
Fix: Always refer to the official documentation or use the `client.list_voices()` method to get a current list of supported voices, their language codes, and SSML genders. This ensures compatibility and avoids errors due to incorrect voice parameters.
gotcha The minimum supported Python version for `google-cloud-texttospeech` is `3.9`. Using older Python versions can lead to installation issues or runtime errors.
Fix: Ensure your development and deployment environments use Python 3.9 or newer. Upgrade your Python installation if necessary.

Install

pip install google-cloud-texttospeech Install stable version

Imports

TextToSpeechClient
```
from google.cloud import texttospeech
```
The TextToSpeechClient is the primary entry point for interacting with the API.
enums and types
```
from google.cloud import texttospeech_v1 as texttospeech
```
For access to enums (e.g., AudioEncoding, SsmlVoiceGender) and types (e.g., SynthesisInput, VoiceSelectionParams), it's common to import the versioned module and alias it.

Quickstart

This quickstart synthesizes a given text into an MP3 audio file. It demonstrates client initialization, defining input text, selecting a voice, configuring audio output, and saving the generated speech. Ensure you have authenticated to Google Cloud, typically via the `GOOGLE_APPLICATION_CREDENTIALS` environment variable or `gcloud auth application-default login`.

import os
from google.cloud import texttospeech_v1 as texttospeech

def synthesize_text(text):
    """Synthesizes speech from the input string of text.

    Ensure GOOGLE_APPLICATION_CREDENTIALS environment variable is set
    or authenticate using `gcloud auth application-default login`.
    """

    # Instantiates a client
    client = texttospeech.TextToSpeechClient()

    # Set the text input to be synthesized
    synthesis_input = texttospeech.SynthesisInput(text=text)

    # Build the voice request, select the language code ('en-US') and the SSML voice gender ('NEUTRAL')
    voice = texttospeech.VoiceSelectionParams(
        language_code="en-US",
        ssml_gender=texttospeech.SsmlVoiceGender.NEUTRAL,
    )

    # Select the type of audio file you want returned
    audio_config = texttospeech.AudioConfig(
        audio_encoding=texttospeech.AudioEncoding.MP3
    )

    # Perform the text-to-speech request
    response = client.synthesize_speech(
        input=synthesis_input,
        voice=voice,
        audio_config=audio_config
    )

    # The response's audio_content is binary. Write it to a file.
    output_filename = "output.mp3"
    with open(output_filename, "wb") as out:
        out.write(response.audio_content)
    print(f'Audio content written to file "{output_filename}"')

if __name__ == "__main__":
    # For local development, set the GOOGLE_APPLICATION_CREDENTIALS environment variable.
    # For example: os.environ['GOOGLE_APPLICATION_CREDENTIALS'] = '/path/to/your/key.json'
    # Or use `gcloud auth application-default login`
    if not os.environ.get('GOOGLE_APPLICATION_CREDENTIALS'):
        print("Warning: GOOGLE_APPLICATION_CREDENTIALS not set. Assuming gcloud ADC is configured.")

    text_to_synthesize = "Hello, world! This is a test of the Google Cloud Text-to-Speech API."
    synthesize_text(text_to_synthesize)

view raw JSON →