Text-to-speech Python SDK

The Voice RSS Text-to-Speech Python SDK wraps Voice RSS Text-to-Speech API.

The Voice RSS Text-to-Speech Python SDKs will help to make integration with our Text-to-Speech API faster and easer.

If you have any questions or suggestions please feel free to contact us via e-mail.

Documentation

To integrate an application with the Voice RSS Text-to-Speech Python SDK it needs to add reference to the package voicerss_tts. The Voice RSS Text-to-Speech Python SDK provides possibility to get speech in binary or Base64 string formats.

Convert text-to-speech as a binary array

The following example demonstrates synchronous converting text-to-speech as a binary array and prints result array:

import voicerss_tts

voice = voicerss_tts.speech({
    'key': '<API key>',
    'hl': 'en-us',
    'v': 'Linda',
    'src': 'Hello, world!',
    'r': '0',
    'c': 'mp3',
    'f': '44khz_16bit_stereo',
    'ssml': 'false',
    'b64': 'false'
})

print(voice)

Convert text-to-speech as a Base64 string

The following example demonstrates synchronous converting text-to-speech as a Base64 string and plays it in an internet browser:

import voicerss_tts

voice = voicerss_tts.speech({
    'key': '<API key>',
    'hl': 'en-us',
    'v': 'Linda',
    'src': 'Hello, world!',
    'r': '0',
    'c': 'mp3',
    'f': '44khz_16bit_stereo',
    'ssml': 'false',
    'b64': 'true'
})

print('<audio src="' + voice['response'] + '" autoplay="autoplay"></audio>')