Google Cloud Text-to-Speech

Google Cloud Text-to-Speech enables developers to synthesize natural-sounding speech with 100+ voices, available in multiple languages and variants. It applies DeepMind’s groundbreaking research in WaveNet and Google’s powerful neural networks to deliver the highest fidelity possible.

It supports multiple languages, including English, German, Polish, Spanish, Italian, French, Portuguese, and Hindi.

This notebook shows how to interact with the Google Cloud Text-to-Speech API to achieve speech synthesis capabilities.

First, you need to set up an Google Cloud project. You can follow the instructions here.

!pip install --upgrade langchain-google-community[texttospeech]

Instantiation

from langchain_google_community import TextToSpeechTool

API Reference:TextToSpeechTool

Deprecated GoogleCloudTextToSpeechTool

from langchain_community.tools import GoogleCloudTextToSpeechTool

API Reference:GoogleCloudTextToSpeechTool

text_to_speak = "Hello world!"

tts = GoogleCloudTextToSpeechTool()
tts.name

We can generate audio, save it to the temporary file and then play it.

speech_file = tts.run(text_to_speak)

Related

• Tool conceptual guide
• Tool how-to guides