How to convert voice to text with QOpenGL
-
I want to display text from an audio file while it is played using QOpenGL, after my researchs, i found Utility Toolkit GLUT allows us to draw text. But is there a library that i can use to draw text from a speech using QOpenGL?
-
@HW-Developer Qt provides support for text to speech but not other way around. You will need to search for some libraries or use cloud based services like https://cloud.google.com/speech-to-text/?utm_source=google&utm_medium=cpc&utm_campaign=emea-de-all-en-dr-skws-all-all-trial-e-gcp-1003963&utm_content=text-ad-none-any-DEV_c-CRE_253520054132-ADGP_Hybrid+|+AW+SEM+|+SKWS+~+EXA_1:1_DE_EN_ML_Speech+API_TOP_speech+to+text-KWID_43700016294628144-kwd-60762121-userloc_9042148&utm_term=KW_speech to text-ST_speech+to+text&ds_rl=1242850&ds_rl=1245734&ds_rl=1245734&gclid=EAIaIQobChMIwP232sv03gIVDpPtCh1b4wEWEAAYASAAEgJBj_D_BwE
-
Hi,
As already written by @jsulm, you need to do text recognition first. There's a wiki entry here about rendering text as 3D objects.
You should also be aware that the text rendering will lag behind the audio being played as the recognition will take time. Therefore, if you want something like a karaoke, you'll have to pre-process the file before playing it.
-
@SGaist I have found voce library for speech recognition and i'am using visual studio but i can't figure out how to link it with my project settings. Is there any one who did use it before ?
-
@HW-Developer
Just an observation: what made you choose that package? I know nothing about it, but it looks like it is from 2005.The most recent of the only 2 posts ever made (https://sourceforge.net/projects/voce/) reads:
I got it to run in Java, but i am still trying to figure out how to get it to work in QT. If anyone knows how to do this, or has heard of it being done before will you please let me know.
which hardly inspires confidence in this one...?
-
@HW-Developer
OK, I don't want to discourage you, maybe you just want to play with it, I've said I have no knowledge. But maybe if that sort of thing was freely available from 2005 there are some more recent ones which might be better?