microsoft text-to-speech platform uses Microsoft Text-to-Speech engine to read a text with natural sounding voices. This component uses an API that is part of the Cognitive Services offering and is known as the Bing Speech API.
You will need an API key, which is free. You can use your Azure subscription or get an API key on the Cognitive Services site.
To enable text-to-speech with Microsoft, add the following lines to your
# Example configuration.yaml entry tts: - platform: microsoft api_key: [YourAPIKey]
- api_key (Required): Your API key.
- language (Optional): The language to use. Defaults to
en-us. Accepted values are listed in the documentation mentioned below. Note that if you set the language to anything other than the default of
en-us, you will need to specify a matching voice type as well.
- gender (Optional): The gender you would like to use for the voice. Accepted values are
Male. Defaults to
- type (Optional): The voice type you want to use. Accepted values are listed as the service name mapping in the documentation. Defaults to
- rate (Optional): Change the rate of speaking in percentage. Example values:
50. Defaults to
- volume (Optional): Change the volume of the output in percentage. Example values:
70. Defaults to
- pitch (Optional): Change the pitch of the output. Example values:
high. Defaults to
- contour (Optional): Change the contour of the output in percentages. This overrides the pitch setting. See the W3 SSML specification for what it does. Example value:
A full configuration sample including optional configuration variables:
# Example configuration.yaml entry tts: - platform: microsoft api_key: XXXXXXXXX language: en-gb gender: Male type: George, Apollo rate: 20 volume: -50 pitch: high contour: (0, 0) (100, 100)