Yandex TTS


The yandextts text-to-speech platform uses Yandex SpeechKit Text-to-Speech engine to read a text with natural sounding voices.

To enable text-to-speech with Yandex SpeechKit, add the following lines to your configuration.yaml:

# Example configuration.yaml entry
tts:
  - platform: yandextts
    api_key: 'XXXXXXXX'

Configuration variables:

  • api_key (Required): API Key for use this service.
  • language (Optional): The language to use. Defaults to en-us. Supported en-EN, ru-RU, uk-UK, tr-TR.
  • codec (Optional): Audo codec. Default is mp3. Supported us mp3, wav, opus.
  • voice (Optional): Speaker voice. Default is zahar. Supported female voices are jane, oksana, alyss, ‘omazh and male voices are zahar and ermil`.
  • emotion (Optional): Speaker emotional intonation. Default is neutral. Also supported are good (freindly) and evil (angry)
  • speed (Optional): Speech speed. Default value is 1. Highest speed is 3 and lowest 0,1

See on api documentation for details. N.B. english version of documentation is outdated. So you could receive api key here

A full configuration sample:

# Example configuration.yaml entry
tts:
  - platform: yandextts
    api_key: 'XXXXX'
    language: 'ru-RU'
    codec: mp3
    voice: oksana
    emotion: evil
    speed: 2