Yandex TTS


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

This integration is working only with old API keys. For the new API keys, this integration cannot be used.

Configuration

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: THE_API_KEY

Configuration Variables

api_keystringRequired

The API Key for use this service.

languagestring(Optional, default: en-US)

The language to use. Supported languages are en-US, ru-RU, uk-UK and tr-TR.

codecstring(Optional, default: mp3)

The audio codec. Supported codecs are mp3, wav and opus.

voicestring(Optional, default: zahar)

The speaker voice. Supported female voices are jane, oksana, alyss, omazh, silaerkan, nastya, sasha, tanya, tatyana_abramova, voicesearch, and zombie. Male voices are zahar, ermil, levitan, ermilov, kolya, kostya, nick, erkanyavas, zhenya, anton_samokhvalov, ermil_with_tuning, robot, dude, and smoky.

emotionstring(Optional, default: neutral)

The speaker emotional intonation. Supported emotions are good (friendly), evil (angry) and neutral

speedfloat(Optional, default: 1)

The speech speed. Highest speed is 3 and lowest 0,1

Please check the API documentation for details. It seems that the English version of documentation is outdated. You could request an API key by email or online.

Full configuration example

The configuration sample below shows how an entry can look like:

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