no problem, hope you’ll find a way to make it work
just made some test and the automation work with elevenlab tts
action: tts.speak
metadata: {}
data:
cache: false
media_player_entity_id: "{{ states('input_select.changeout') }}"
message: "{{ rep.response.speech.plain.speech }}"
target:
entity_id: tts.elevenlabs
Nice I’ll try. This is what I currently have with Piper TTS, and it’s working.
alias: ollamaspeak
description: ""
triggers:
- trigger: conversation
command: "{question}"
conditions: []
actions:
- action: assist_satellite.announce
data:
preannounce: true
media_id:
media_content_id: media-source://media_source/local/button-3.wav
media_content_type: audio/x-wav
metadata:
title: button-3.wav
thumbnail: null
media_class: music
children_media_class: null
navigateIds:
- {}
- media_content_type: app
media_content_id: media-source://media_source
target:
device_id: 123456789
- action: conversation.process
metadata: {}
data:
agent_id: conversation.ollama_conversation
text: "{{trigger.slots.question }}"
response_variable: rep
- set_conversation_response: Stand by
- data:
cache: false
message: "{{ rep.response.speech.plain.speech }}"
media_player_entity_id: media_player.bedroom_speaker
options:
voice: en_GB-northern_english_male-medium
action: tts.speak
target:
entity_id: tts.piper
mode: single
Is it a good idea to include your voice code in your posts? I think that’s how Elevenlabs charge for usage…
No joy for me. It’s odd as it works in the VA.
This is what I have …
data:
cache: false
message: "{{ rep.response.speech.plain.speech }}"
options:
voice: 123456789
media_player_entity_id: media_player.bedroom_speaker
action: tts.speak
target:
entity_id: tts.elevenlabs
enabled: true
Odd for sure . Did you try without option?
Yeah I did
I’m not home for now but i will work on it tomorow maybe i will have a "bulb"moment with more sleep😅
OK it was my API credits! My working config:
Though for some reason I can’t get the automation to trigger it with dynamic prompts. The test works though.
alias: Elevenlabs test
data:
cache: true
message: This is a test.
media_player_entity_id: media_player.bedroom_speaker
action: tts.speak
enabled: true
target:
entity_id:
- tts.elevenlabs_2
See more: ElevenLabs - Home Assistant
alias: ollamaspeak
description: ""
triggers:
- trigger: conversation
command: "{question}"
conditions: []
actions:
- action: assist_satellite.announce
data:
preannounce: true
media_id:
media_content_id: media-source://media_source/local/button-3.wav
media_content_type: audio/x-wav
metadata:
title: button-3.wav
thumbnail: null
media_class: music
children_media_class: null
navigateIds:
- {}
- media_content_type: app
media_content_id: media-source://media_source
target:
device_id: 123456789
enabled: false
- action: conversation.process
metadata: {}
data:
text: "{{trigger.slots.question }}"
agent_id: conversation.ollama_conversation
response_variable: rep
- set_conversation_response: "{{ rep.response.speech.plain.speech }}"
- data:
cache: false
message: "{{ rep.response.speech.plain.speech }}"
media_player_entity_id: media_player.bedroom_speaker
options:
voice: en_GB-northern_english_male-medium
action: tts.speak
target:
entity_id: tts.elevenlabs_2
mode: single
can you try this?
Yep it’s working now. I found my API key had a limit of 50 - I thought this was a sensible safety (alternative to “Unlimited”). However it seems like this is “Credits” or some sort of query/token count, rather than $50! I set it to unlimited as I see it’s coming off my free credits still - albeit rather quickly.