Hello, I need to add Speech to text feature in RASA, where user can ask questionsusing his voice and bot will answer him by chat. Does anyone know how can I do it in RASA? As my front-end will be an Android Application. Kindly do tell me how to do it.
Thanks in Advance.
I think that the best is to use directly the native speech-to-text feature of android. You will get the text directly in your app. Many tuto on internet …
But then how am I supposed to connect it to my data which is stored in rasa?
It depends on many factors.
Most common use would be to expose your RASA server on the internet (in a secured way), then use the HTTP API (POST your text from the mobile device to the RASA server) and get the intent/answer back (there is a good explanation about creating custom channels for your rasa server). The only special point of your project is that the mobile device should listen and transcribe text as the source of the chat. On the other way, you just have to display the answer of RASA back in the chat window.
As an alternative I can recommend you try to convert audio to text online automaticallly or manually. It depends on your needs: if you want to get a high-quality product with 100% accuracy, you’d better use professional transcription. But if you want to get your file as soon as possible, try automatic transcription.