About
How does Vocofy work?
The Vocofy team made an artificial intelligence model to distinguish Cantonese cadence, different people’s articulation, pronunciation, exhalation, speaking rhythm, etc., and then generated speech through artificial intelligence learning and calculation. Vocofy repeatedly and flexibly utilizes Text-to-Speech (TTS) technology and builds its own Chinese Cantonese pronunciation font library.
At Vocofy, we help patients who have lost their voice through a doctor’s referral. After a doctor’s diagnosis confirms the chances of losing the voice, we provide recording equipment and tutorials to the patients immediately. After the recording period (as much data as we can collect), we analyze the raw data and work on the transcription to build a tailor-made voice model for each patient. Once the AI model is complete, we deploy it to our mobile phone app and provide an “app-use” tutorial to the patient. Patients who have lost their voice are eligible to use Vocofy AI permanently.
Acknowledgment
