Unable to call TTS via elevenlabs in dev tools but works elsewhere

I have just set up ElevenLabs integration and it all works fine when I play tts from the media player:

However, when I try to create a service call in dev tools it does not work (using the same yaml from integration docs)

yaml:

action: tts.speak
target:
  entity_id: tts.elevenlabs
data:
  media_player_entity_id: media_player.main_bedroom_speaker
  message: Hello, can you hear me now?

error logs:

Logger: homeassistant.components.tts
Source: components/tts/__init__.py:1064
integration: Text-to-speech (TTS) (documentation, issues)
First occurred: 16:56:26 (1 occurrences)
Last logged: 16:56:26

Error on load tts: 4b00795a5f1834a60797d268e9e6c0c56e1900c0_en_-_tts.elevenlabs not in cache!

and

Logger: homeassistant.components.cast.media_player
Source: components/cast/media_player.py:405
integration: Google Cast (documentation, issues)
First occurred: 16:56:26 (1 occurrences)
Last logged: 16:56:26

Failed to cast media http://192.168.1.105:8123/api/tts_proxy/4b00795a5f1834a60797d268e9e6c0c56e1900c0_en_-_tts.elevenlabs.mp3 from internal_url (http://192.168.1.105:8123). Please make sure the URL is: Reachable from the cast device and either a publicly resolvable hostname or an IP address

How do I resolve this please?

I had the same issue, and was about to ask you if you find a solution… Then I decided to test adding the voice as option as follow and it works:

action: tts.speak
target:
  entity_id: tts.elevenlabs
data:
  media_player_entity_id: media_player.media_playerX
  message: "Test 1 2 3"
  options:
    voice: Alice

Noticed that you need to the voice name start with capital letter as in the available voices in ElevenLabs

Seems that I missed a lot using only Google TTS. ElevenLabs seems to be much more nature and can read different language, without even specify that language

1 Like