[Summary] I tried to compare which sentence reading software to read the most sentences and texts like a human
Jan. 17, 2021
Hello, this is Ondoku.
What are you most worried about when you are looking for text-to-speech software?
- Is it free or paid?
- Can you read it like a human?
- Can the speed and height be adjusted?
These are the three areas that are of great concern.
Especially, "Does it read like a human" is a very important issue for the listener.
The text-reading software industry is evolving steadily.
This time,
- Sites that support Japanese
- Adjustable
Under the condition, I tried to find out which text-reading software reads the most human-like reading software.
Famous sentence reading software
If you look up the text reading software, you can see that there are quite a lot of software.
However, if you look closely, it is easy to see that the patterns of the same voice synthesis engine are the same even though the software is different.
Example) Stick reading and Softoke have the same voice synthesis engine
If the voice synthesis engine is the same, the sound quality will be the same, so in this verification we will treat it as the same even if the software is different.
Paid sentence reading software
- AI talk
- VOICEROID
- Ichitaro (Document creation software)
Free text-to-speech software
- Text talk
- SoftTalk
- Stick reading
- Coe station
- Ondoku
Criteria for humanity of text-to-speech software
Different people have different criteria for how humans read text.
- Do you read aloud emotionally?
- Whether to speak with inflection while keeping a good interval
- Whether to put exclamation or breath sounds
What kind of thing makes people speak text-reading software like a human being?
Really this is different for each person.
This time, the standard of reading out like a human is
You can read aloud without any discomfort in intonation while taking a proper amount of time.
Let's put emphasis on that and compare them.
This is because there is only paid text-reading software when it comes to the function of reading with emotion.
I would like to introduce while including the free ones as comparison targets, so let's compare with this standard this time.
Manuscript to be compared
In order to make a comparison, you need to have the text-reading software read the manuscript.
This time, there are several, so I made it a short manuscript, and I made it a manuscript for the weather forecast that does not make me feel uncomfortable even if I have no feelings.
The national weather forecast.
On the Pacific Ocean side such as Tokyo, dry and sunny weather continues.
Let's try to prevent a cold.
The temperature from noon to night.
The cold like January will continue nationwide.
Then, actually have the text-to-speech software read aloud.
You can play the actual audio by clicking the play button (▶).
Text talk
SoftTalk and Stick Reading
Ondoku
Voice assistant
Announcer A
Announcer B
AI talk
Hope
Kaho
Nanako
politics
Apricot
VOICEROID
VOICEROID+ Kyomachi Seika
VOICEROID+ Tohoku Kiritan
Ichitaro (Document creation software)
We have excluded it because we need to synthesize it with our own voice.
Also, I do not own Ichitaro, so please listen to it by voice, not by voice synthesis.
The text-to-speech software that can be used free of charge allows you to read like a human
- Ondoku
- Text talk
- Stick reading
Texto is worried about the mechanical sound like a key sound,
Stick reading is worried about the muffled voice,
I think that there are different points, so there are different tastes.
If you can use it for a fee
- VOICEROID
- AI talk
It was the impression that they were reading like humans in this order.
Also, if you can use it for a fee, some of them have a function to add emotion and intonation to the voice.
With such options, it seems that the range of voice usage will expand further.
Which software you use depends on your preference.
If you are also considering commercial use on this, please also refer to this article as it also summarizes commercial use of each software.
I look forward to seeing you.
■ AI voice synthesis software "Ondoku"
"Ondoku" is an online text-to-speech tool that can be used with no initial costs.
- Supports approximately 50 languages, including Japanese, English, Chinese, Korean, Spanish, French, and German
- Available from both PC and smartphone
- Suitable for business, education, entertainment, etc.
- No installation required, can be used immediately from your browser
- Supports reading from images
To use it, simply enter text or upload a file on the site. A natural-sounding audio file will be generated within seconds. You can use voice synthesis up to 5,000 characters for free, so please give it a try.
Email: ondoku3.com@gmail.com
"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