Faire en sorte que l'utilisateur utilise sa voix pour interagir avec le système(Speech to text)

Je suis en train de developer un VOIP avec Asterisk.
Au cours de ce processus, j’aimerais intégrer la synthèse vocale pour activer les différentes commandes avec la voix.

But… what is your question (preferably in English)?


The subject says “speech to text”, but I presume that “synthèse vocale” means text to speech. Which is it.

A lot of people use Google for both, but there are privacy issues with that, and you are also vulnerable to the availability of Google’s services. I think Google only provide continuous speech recognition. For many applications you will get a more reliable result with recognition of single words and short phrases, with a limited vocabulary.

There is some general information in Speech Recognition and Text-to-Speech

Specifically for speech recognition, see https://wiki.asterisk.org/wiki/display/AST/Speech+Recognition+API , however, you will need third party, probably commercial code, for this to work.

thank you for your interest in my project
my question is how can I integrate speech to text in a VOIP project with Asterisk, instead of using the dial keys

thank you for your interest in my project
I will explore the link you sent me and come back to you with something new

This topic was automatically closed 30 days after the last reply. New replies are no longer allowed.