2024.11.0
Home ▸ Integrations ▸

IBM Watson TTS

The watson_tts text-to-speech integrationIntegrations connect and integrate Home Assistant with your devices, services, and more. [Learn more] that works with IBM Watson Cloud to create the spoken output. Watson is a paid service via IBM Cloud but there is a decent free tier which offers 10000 free characters every month.

Setup

For supported formats and voices please go to IBM Cloud About section.

To get started please read the Getting started tutorial.

Configuration

To configure Watson TTS, add the following lines to your configuration.yamlThe configuration.yaml file is the main configuration file for Home Assistant. It lists the integrations to be loaded and their specific configurations. In some cases, the configuration needs to be edited manually directly in the configuration.yaml file. Most integrations can be configured in the UI. [Learn more] file. After changing the configuration.yamlThe configuration.yaml file is the main configuration file for Home Assistant. It lists the integrations to be loaded and their specific configurations. In some cases, the configuration needs to be edited manually directly in the configuration.yaml file. Most integrations can be configured in the UI. [Learn more] file, restart Home Assistant to apply the changes. The integration is now shown on the integrations page under Settings > Devices & services. Its entities are listed on the integration card itself and on the Entities tab.

# Example configuration.yaml entry
tts:
  - platform: watson_tts
    watson_apikey: YOUR_GENERATED_APIKEY

You can get these tokens after you generated the credentials on the IBM Cloud console:

Configuration Variables

Looking for your configuration file?
watson_url string (Optional)

The endpoint to which the service will connect.

Default:

https://api.us-south.text-to-speech.watson.cloud.ibm.com

watson_apikey string Required

Your secret apikey generated on the IBM Cloud admin console.

voice string (Optional, default: en-US_AllisonV3Voice)

Voice name to be used.

output_format string (Optional, default: audio/mp3)

Override the default output format. Supported formats: audio/flac, audio/mp3, audio/mpeg, audio/ogg, audio/ogg;codecs=opus, audio/ogg;codecs=vorbis, audio/wav

Usage

Say to all media_player device entities:

- action: tts.watson_tts_say
  data:
    message: "Hello from Watson"

or

- action: tts.watson_tts_say
  data:
    message: >
      <speak>
          Hello from Watson
      </speak>

Say to the media_player.living_room device entity:

- action: tts.watson_tts_say
  target:
    entity_id: media_player.living_room
  data:
    message: >
      <speak>
          Hello from Watson
      </speak>

Say with break:

- action: tts.watson_tts_say
  data:
    message: >
      <speak>
          Hello from
          <break time=".9s" />
          Watson
      </speak>

Optionally, specify a voice for the message:

- action: tts.watson_tts_say
  data:
    message: "Hello from Watson"
  options:
    voice: en-US_EmilyV3Voice

Related topics