Hello guys,
I have a question to all of you that use deepspeech in production.
I’m working on the multi-modal digital assistant. I’m applying Deepspeech in the stt component.
I am not sure how to calculate a price of using DeepSpeech in the stt component for a customer.
Which parameter should I take into account? Do you have any hints for me? Duration of an input message? The complexity of the request? Are there any ‘standards’/ pricing model that we should follow? Let assume that the assistant can speak only in one language, use custom vocabulary and has some sec of latency.
i will be very thankful for any advice!