Text-To-Speech

Text-To-Speech (TTS) is the process of synthesizing audio from text. Mycroft uses our own TTS engines by default, however we also support a range of third party services.

Mycroft has two open source TTS engines.

Mimic 1 is a fast, light-weight engine based on Carnegie Mellon University's FLITE software. Whilst the original Mimic may sound more robotic, it is able to be synthesized on your device.

Mimic 2 is an implementation of Tacotron speech synthesis. It is a fork of Keith Ito's project with additional tooling and code enhancements. Mimic 2 provides a much more natural sounding voice, however requires significant processing power to do so and is therefore cloud-based.

Default Engine

The engine that will be used depends on the voice selected in your Device Settings at Home.mycroft.ai.

Currently:

  • British Male is Mimic 1

  • American Female is Mimic 1

  • American Male is Mimic 2

  • Google Voice uses the Google Translate TTS API.

As Mimic 1 voices can be synthesized on device, the British Male voice will be used anytime the device cannot reach your preferred TTS service. This allows Mycroft to continue to speak even if it is not connected to a network.

eSpeak

A multi-lingual software speech synthesizer for Linux and Windows.

eSpeak uses a "formant synthesis" method. This allows many languages to be provided in a small size. The speech is clear, and can be used at high speeds, but is not as natural or smooth as larger synthesizers which are based on human speech recordings.

Mycroft Configuration

First, ensure that the espeak package is installed on your system.

sudo apt-get install espeak

Then, using the Configuration Manager we can edit the mycroft.conf file by running:

mycroft-config edit user

To our existing configuration values we will add the following:

"tts": {
"module": "espeak",
"espeak": {
"lang": "english-us",
"voice": "m1"
}
}

Mary TTS

The multilingual open-source MARY text-to-speech platform. MaryTTS is a client-server system written in pure Java, so it runs on many platforms.

Server Setup

The latest installation instructions can be found on the MaryTTS Github repository.

Mycroft Configuration

Using the Configuration Manager we can edit the mycroft.conf file by running:

mycroft-config edit user

To our existing configuration values we will add the following:

"tts": {
"marytts": {
"url": "http://YOUR_SERVER:PORT_NUMBER"
},
"module": "marytts"
}

FA TTS

Produced by Mivoq, it is based off Mary TTS.

Server Setup

The latest installation instructions can be found on the Mivoq FA TTS Github repository.

Mycroft Configuration

Using the Configuration Manager we can edit the mycroft.conf file by running:

mycroft-config edit user

To our existing configuration values we will add the following:

"tts": {
"fatts": {
"url": "http://YOUR_SERVER:PORT_NUMBER"
},
"module": "fatts"
}

Amazon Polly

Amazon Polly's text-to-speech service.

Account Setup

Create an AWS account and add the Polly service.

You will need to take note of your private "Access Key ID" and "Secret Access Key".

Mycroft Configuration

First, check the list of available voices and languages. Note that Polly does not provide a separate langauge attribute like other TTS options. The language is determined by which voice is chosen.

Then, install the boto3 python module in the Mycroft virtual environment:

mycroft-pip install boto3

or

cd ~/mycroft-core
source .venv/bin/activate
pip3 install boto3
deactivate

Finally, using the Configuration Manager we can edit the mycroft.conf file by running:

mycroft-config edit user

To our existing configuration values we will add the following:

"tts": {
"module": "polly",
"polly": {
"voice": "Matthew",
"region": "us-east-1",
"access_key_id": "YOUR_ACCESS_KEY_ID",
"secret_access_key": "YOUR_SECRET_ACCESS_KEY"
}
}

If the voice and region attributes are ommitted the defaults of Matthew and us-east-1 will be used. This is an English (US) voice.

Google TTS

Google Translate's text-to-speech API.

Mycroft Configuration

Using the Configuration Manager we can edit the mycroft.conf file by running:

mycroft-config set tts.module "google"

IBM Watson

Account Setup

Create an account at IBM.com/cloud. Once you add the TTS service to your account, you will receive an API key and unique API url.

You can find a list of available voices at Languages and Voices. For example, "en-US_MichaelV3Voice".

IBM keeps a log of all requests in the lite plan unless you turn it off explicitly by setting "X-Watson-Learning-Opt-Out" to true. We have set Mycroft to Opt-Out by default, so if you want to share data with IBM then you must set this to false.

Mycroft Configuration

Using the Configuration Manager we can edit the mycroft.conf file by running:

mycroft-config edit user

To our existing configuration values we will add the following:

"tts": {
"module": "watson",
"watson": {
"voice":"PREFERRED_VOICE",
"apikey": "YOUR_API_KEY",
"url": "YOUR_API_URL",
"X-Watson-Learning-Opt-Out": "true"
}
}

Microsoft Azure

Account Setup

Create a Microsoft Azure account and get a server access token.

Mycroft Configuration

Using the Configuration Manager we can edit the mycroft.conf file by running:

mycroft-config edit user

To our existing configuration values we will add the following:

"tts": {
"module": "bing",
"bing": {
"api_key": "YOUR_API_KEY",
"format": "riff-16khz-16bit-mono-pcm",
"gender": "Male"
}
}

Responsive Voice

The API for this service may have significantly changed. As such this TTS option may not be available. Contributions to restore the service are warmly welcomed. Please direct any development questions to the ~Dev channel of Mycroft Chat.

Lifelike human digital voices from ResponsiveVoice.org.

Mycroft Configuration

Using the Configuration Manager we can edit the mycroft.conf file by running:

mycroft-config edit user

To our existing configuration values we will add the following:

"tts": {
"module": "responsive_voice",
"responsive_voice": {
"gender": "male",
"pitch": "0.5",
"rate": "0.5",
"vol": "1"
}
}

SpdSay

A common high-level interface to speech synthesis from Free(B)Soft.

Software Setup

Install the speech-dispatcher package using your systems package manager. For example: sudo apt-get install speech-dispatcher

Mycroft Configuration

Using the Configuration Manager we can edit the mycroft.conf file by running:

mycroft-config set tts.module "spdsay"

Yandex SpeechKit

Speech services from Yandex, one of the largest cloud platforms in Russia.

Account Setup

  1. Register an account at Yandex.

  2. Create billing account: https://cloud.yandex.com/docs/billing/quickstart/#create_billing_account

    You can activate a free trial period in the console.

  3. Create first "folder" in cloud.

  4. Create service account for you Mycroft instance with role editor: https://cloud.yandex.com/docs/iam/operations/sa/create

Mycroft Configuration

Using the Configuration Manager we can edit the mycroft.conf file by running:

mycroft-config edit user

To our existing configuration values we will add the following:

"tts": {
"module": "yandex",
"yandex": {
"lang": "en-US",
"api_key": "YOUR_API_KEY",
"voice": "oksana", #optional
"emotion": "good" #optional
}
}