[Request response to Ondoku] Please do not count the number of characters when corrected.
Dec. 13, 2023
Hello, this is Ondoku.
At Ondoku, we receive inquiries and requests from various customers every day.
This time, in such an inquiry,
- After reading the text aloud, I slightly revised it. I don't want the number of characters to be counted when the revised text is read aloud again.
I received this question and request.
Same thing this time
“It feels like a waste to have only slightly revised characters counted.”
Since some people may be thinking about this, I will write an answer to this request on my blog.
If you modify it, please do not count the number of characters.
Text-to-speech software uses something called a "speech synthesis engine" in many situations.
What is a speech synthesis engine?
In general, a device that creates voice by calling pre-recorded voice data from input characters and connecting them.
Ondoku has a separate contract for this "speech synthesis engine".
Specifically, every time you read aloud, Ondoku pays a fee to the text-to-speech engine.
This is something that Ondoku cannot control and will definitely incur charges.
In case of correction,
Ondoku has a unique system that allows you to call up audio from your past reading history, as long as it's something you've read aloud before (settings/text).
Therefore, the number of characters will not be counted if it is "something that has been read out before (settings/text)".
- Even one character can change the text that is read aloud,
- Setting values such as speed and height change even by 1,
- Change the tone of voice when reading aloud
Then, it will judge it as "text that has never been read aloud before" and will read it out loud.
Of course, since this is "text that has never been read out before," there will be a usage fee for the speech synthesis engine.
Unfortunately, speech synthesis engines are not as flexible as humans.
Here, I recommend that smart people use the inflexible machines to their advantage.
At Ondoku, when detailed reading is required, such as when creating a YouTube narration, we recommend reading aloud in as few characters as possible.
Requests for experience are welcome!
As a service creator, I am very grateful to receive such requests and inquiries.
This is because when creating a service, it is very difficult to find out what the customer's needs are and what they want.
Under such circumstances, by receiving inquiries like this, it is a very meaningful email that allows us to find out the direction of Ondoku's development by knowing what you want Ondoku to do.
Ondoku will continue to evolve day by day to become a service that is easy to use for you.
If you have any questions, please feel free to contact us.
Fan letters and messages like ``easy to use'' are also very welcome.
I'm very happy because there are many times when people don't send me happy messages even if they think about it.
We look forward to your continued support of Ondoku.
"Ondoku" is a Text-to-Speech service that anyone can use for free without installation. If you register for free, you can get up to 5000 characters for free each month. Register now for free