#Microphone icon iOS app
1 messages · Page 1 of 1 (latest)
The microphone shows when it’s listening and streaming voice to the voice assistant. Did you set up a voice assistant?
Yes I created an assistant, but I talk to the app and nothing happens
There's a cryptic message in my logs
Traceback (most recent call last):
File "/usr/src/homeassistant/homeassistant/components/websocket_api/decorators.py", line 28, in _handle_async_response
await func(hass, connection, msg)
File "/usr/src/homeassistant/homeassistant/components/assist_pipeline/websocket_api.py", line 239, in websocket_run
await pipeline_input.validate()
File "/usr/src/homeassistant/homeassistant/components/assist_pipeline/pipeline.py", line 1555, in validate
raise PipelineRunValidationError(
"the pipeline does not support speech-to-text"
)
homeassistant.components.assist_pipeline.pipeline.PipelineRunValidationError: the pipeline does not support speech-to-text
The actual message is this: "the pipeline does not support speech-to-text"
In your Voice Assistant settings you need to add a STT provider to the pipeline.
Probably good to read through this: https://www.home-assistant.io/voice_control/
Actually, that just jumps off to two links.
Open source home automation that puts local control and privacy first. Powered by a worldwide community of tinkerers and DIY enthusiasts. Perfect to run on a Raspberry Pi or a local server.
Is there any way to use ChatGPT or it has to be a local model?
Yea. You can use ChatGPT. You need a STT processor, an agent (like ChatGPT), and then a TTS processor.
Can I use a cloud STT that is not home assistant cloud?
I don’t know if anyone has built one. Maybe?
https://www.home-assistant.io/integrations/#speech-to-text
Looks like Google Cloud is an option. Nabu Casa is on Azure.