First, you must have a PC or laptop with audio capabilities and a good quality consumer-grade (or better) head-mounted microphone. When you are registered and set up to record, you will then carefully record a short inventory of 10 sentences for us to review. The recording tool will guide you through that process by prompting you for each sentence that is needed. After you upload these test speech files to our server, we will look them over and possibly make suggestions for creating better recordings.
If all is well, you will be able to start voice banking using one of our fixed lists of sentences: either our standard list of 3155 sentences, or our new, experimental “Gen3” list of 300 sentences. It is not necessary to record all the sentences in the list, but they are there for anyone who wants to create the very best possible sounding voice. Although most sentences are fairly short, the time to record them may be longer than you expect. Because the list is recorded one sentence at a time, and it may take more than one try to get a sentence right, you should expect that recording the standard list will take 15 hours or more distributed over multiple days; for some people, it can take a lot longer. The “Gen3” list can possibly be recorded over a few hours. Further, those lists can be supplemented by adding Custom sentences that you would like to record.
When all of the sentences are recorded, we will convert your recordings to a synthetic voice. This may take several days. As soon as it is ready, we will send you a web link to allow you to listen to several versions of your voice and select the one you like most.