Azure Speech

The AzureTTSService provides professional, natural-sounding speech using Azure Cognitive Services. It's the recommended TTS provider for enterprise-grade applications requiring massive scale and extensive voice support.

Installation

To use Azure TTS, install the required dependencies:

pip install "piopiy-ai[azure]"

Prerequisites

• An Azure subscription and a Speech service resource (Get yours here).
• Azure API key and region.
• Set your credentials in your environment:

  export AZURE_SPEECH_API_KEY="your_api_key_here"
  export AZURE_SPEECH_REGION="your_region_here"

Configuration

AzureTTSService Parameters

Parameter	Type	Default	Description
api_key	str	Required	Your Azure Speech API key.
region	str	Required	Azure region (e.g., "eastus").
voice	str	"en-US-SaraNeural"	Azure voice identifier.
params	InputParams	InputParams()	Advanced prosody and style settings.

InputParams

Parameter	Type	Default	Description
style	str	None	Speaking style (e.g., "cheerful").
pitch	str	None	Voice pitch adjustment.
rate	str	"1.05"	Speech rate multiplier.
volume	str	None	Volume level adjustment.

Usage

Basic Setup

import os
from piopiy.services.azure.tts import AzureTTSService

tts = AzureTTSService(
    api_key=os.getenv("AZURE_SPEECH_API_KEY"),
    region=os.getenv("AZURE_SPEECH_REGION"),
    voice="en-US-EmmaNeural"
)

With Expressive Styles

from piopiy.services.azure.tts import AzureTTSService

tts = AzureTTSService(
    api_key=os.getenv("AZURE_SPEECH_API_KEY"),
    region="eastus",
    params=AzureTTSService.InputParams(
        style="cheerful",
        rate="1.1"
    )
)

Notes

• Word Timestamps: AzureTTSService supports precise word-level timestamps, enabling synchronized visual feedback or animations.
• SSML: The service automatically generates SSML to apply your configuration parameters efficiently.