How getting continuous speech recognition in Thunkable?

hi

I would like my project to have a voice interface as much as possible but I find the appearance of the keyboard not very aesthetic or user friendly
how to bring up the voice recognition button from google or other?

What are you doing to make the keyboard appear for speech-to-text? Which blocks are you using?

Which API do you want to use instead of the Thunkable speech recognizer?

Hi

The keyboard appears when you click on a textbox i would like to jump this
for the moment I use the voice input linked to the use of the google keyboard

If you’re using the voice input from Google keyboard then you can’t avoid this problem. What you can do instead is to use the built-in speech recognition in Thunkable or an API. In those cases, the keyboard won’t appear.

Hi

I will try to follow this lead but maybe with you an API to advise me
I plan to make a simple application for taking orders (not for a restaurant) but in a warehouse; reduced and specific vocabulary

I’m using the built-in speech recognition block for my AI chat app. Configuring APIs for things like this can be complicated but it should be possible. For me, the Thunkable speech recognition works pretty well so I didn’t end up using an API for that.

I do use a Google Cloud Voice API for text-to-speech because of the far superior sound of the voice and more natural pacing of speech when compared to Thunkable’s text-to-speech block. You might look at this: https://cloud.google.com/speech-to-text.

hi

i tried the built-in speech recognition block
listening is done in a rather short time

is it possible to implement the web speech api in thunkable ?

Sure

I look on the side of codepen I found a rather light Pen that could suit me but implementing it is another story

the Pen

https://codepen.io/Ishaanbedi/pen/dyoxKBz

Is that an API? It just looks like a script.

no this is not an api (it seems even more complicated to implement)

I did a test with the thunkable webrowser which pointed to this Pen it doesn’t work ( i can press the button but i can’t see what i’m saying)

i looked for an api but it’s not free

i found something called deepspeech

I am looking for a solution that I understand

I break my head against the walls because Thunkable’s voice recognition is too short :unamused:

update

this Pen works in the Thunkable Webrowser

https://codepen.io/alexandra_ioan/pen/wOgdYG

You could try what I suggested. It’s not free but the pricing doesn’t look too bad to me:

This topic was automatically closed 90 days after the last reply. New replies are no longer allowed.