Google Cloud TTS

The GoogleHttpTTSService provides professional, high-quality text-to-speech synthesis using Google Cloud's extensive library of neural and standard voices. It supports comprehensive SSML for fine-grained control and features advanced Chirp and Journey models for conversational excellence.

Installation

To use Google Cloud TTS, install the required dependencies:

pip install "piopiy-ai[google]"

Prerequisites

• A Google Cloud project with the Text-to-Speech API enabled (Get yours here).
• Set your credentials in your environment:

  export GOOGLE_APPLICATION_CREDENTIALS="path/to/your/service-account.json"

Configuration

GoogleHttpTTSService Parameters

Parameter	Type	Default	Description
credentials	str	None	JSON string of service account credentials.
credentials_path	str	None	Path to service account JSON file.
voice_id	str	"en-US-Chirp3-HD-Charon"	Google TTS voice ID.
sample_rate	int	None	Audio sample rate in Hz.
params	InputParams	InputParams()	Advanced styling and prosody settings.

InputParams

Parameter	Type	Default	Description
pitch	str	None	Voice pitch adjustment (e.g., "+2st", "-50%").
rate	str	None	Speaking rate (SSML) (e.g., "slow", "fast").
speaking_rate	float	None	Speaking rate (Chirp/Journey) [0.25, 2.0].
volume	str	None	Volume adjustment (e.g., "loud", "+6dB").
emphasis	str	None	Text emphasis level (strong, moderate, etc.).
language	Language	Language.EN	Language for synthesis.
gender	str	None	Preferred voice gender.
google_style	str	None	Speaking style (apologetic, calm, empathetic, etc.).

Usage

Basic Setup

import os
from piopiy.services.google.tts import GoogleHttpTTSService

tts = GoogleHttpTTSService(
    voice_id="en-US-Journey-F"
)

With Advanced Styles (Chirp 3)

from piopiy.services.google.tts import GoogleHttpTTSService

tts = GoogleHttpTTSService(
    voice_id="en-US-Chirp3-HD-Charon",
    params=GoogleHttpTTSService.InputParams(
        speaking_rate=1.1,
        gender="male"
    )
)

Notes

• Service Authenticated: This service requires valid Google Cloud credentials to be available via environment variables or explicitly passed.
• Model Support: Chirp and Journey voices represent Google's latest conversational technology and do not support standard SSML tags; use speaking_rate for these models instead.
• Output Format: Piopiy automatically handles the removal of WAV headers for seamless streaming playback.