Skip to main content

Simple Test-To-Speech (TTS) interface library with multi-language and multi-engine support.

Project description

Simple Text-To-Speech (TTS) interface library with multi-language and multi-engine support.

https://travis-ci.org/grigi/talkey.svg https://coveralls.io/repos/grigi/talkey/badge.svg?branch=master&service=github

Documentation: http://talkey.readthedocs.org/

Rationale

I was really intrigued by the concept of jasper, a voice-controlled interface. I needed it to be multi-lingual like me, so this library is my attempt to make having the TTS engines multi-lingual. A lot of this code is inspired by the Jasper project.

Basic Usage

Install from pypi:

pip install talkey

At its simplest use case:

import talkey
tts = talkey.Talkey()
tts.say('Old McDonald had a farm')

If you get a talkey.base.TTSError: No supported languages error, it means that you don’t have a supported TTS engine installed. Please see below.

By default it will try to locate and use the local instances of the following TTS engines:

  • Flite
  • SVOX Pico
  • Festival
  • eSpeak
  • mbrola via eSpeak

Installing one or more of those engines should allow the libary to function and generate speech.

It also supports the following networked TTS Engines:

  • MaryTTS (needs hosting)
  • Google TTS (cloud hosted)

For best results you should configure it:

import talkey
tts = talkey.Talkey(
    # These languages are given better scoring by the language detector
    # to minimise the chance of it detecting a short string completely incorrectly.
    # Order is not important here
    preferred_languages=['en', 'af', 'el', 'fr'],

    # The factor by which preferred_languages gets their score increased, defaults to 80.0
    preferred_factor=80.0,

    # The order of preference of using a TTS engine for a given language.
    # Note, that networked engines (Google, Mary) is disabled by default, and so is dummy
    # default: ['google', 'mary', 'espeak', 'festival', 'pico', 'flite', 'dummy']
    # This sets eSpeak as the preferred engine, the other engines may still be used
    #  if eSpeak doesn't support a requested language.
    engine_preference=['espeak'],

    # Here you segment the configuration by engine
    # Key is the engine SLUG, in this case ``espeak``
    espeak={
        # Specify the engine options:
        'options': {
            'enabled': True,
        },

        # Specify some default voice options
        'defaults': {
                'words_per_minute': 150,
                'variant': 'f4',
        },

        # Here you specify language-specific voice options
        # e.g. for english we prefer the mbrola en1 voice
        'languages': {
            'en': {
                'voice': 'english-mb-en1',
                'words_per_minute': 130
            },
        }
    }
)
tts.say('Old McDonald had a farm')

Installing TTS engines

Ubuntu/Debian:

For festival:

sudo apt-get install festival

For flite:

sudo apt-get install flite

For SVOX Pico:

sudo apt-get install libttspico-utils

For eSpeak:

sudo apt-get install espeak

For mbrola and en1 voice:

sudo apt-get install mbrola-en1

Windows:

Install eSpeak:

Go to http://espeak.sourceforge.net/download.html and download and install setup_espeak-<version>.exe

For mbrola and its voices:

Go to http://espeak.sourceforge.net/mbrola.html and download and install MbrolaTools<version>.exe and follow directions to install voices from http://www.tcts.fpms.ac.be/synthesis/mbrola/mbrcopybin.html

For google TTS:

install python package gTTS

Download ffmpeg from http://ffmpeg.zeranoe.com/builds/

Extract with 7Zip, and add the bin folder to the PATH.

e.g.:
extract to C:ffmpeg and add C:ffmpegbin to the PATH

(In cmd.exe you should be able to just run ffmpeg and see it showing information, then it is working right)

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Filename, size & hash SHA256 hash help File type Python version Upload date
talkey-0.1.1.tar.gz (15.3 kB) Copy SHA256 hash SHA256 Source None

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN SignalFx SignalFx Supporter DigiCert DigiCert EV certificate StatusPage StatusPage Status page