We’re excited to introduce two new voices to our ever-expanding roster, including the first male Canadian-French voice ever! Now that Leo and Beth are completely integrated into all of our product offerings, consumers and developers can further customize their text-to-speech programs.
Beth, our newest US English voice, and Leo, our first male French-Canadian voice, increase the bar for excellent speech synthesizers. These are both exceptional voices, but we don’t generally like to boast.
Leo is who?
The text-to-speech voice Leo is French Canadian, and he captures the charm of the French-Canadian accent admirably. He manages to combine a deep, refined tone with his voice. Leo’s voice has been characterized as friendly and authoritative, making it ideal for corporate applications. When a customer calls your business and hears Leo’s voice, they will be immediately intrigued.
Leo is perfect for announcement systems, broadcasting, eReading, and personal usage. He can also be used for IVR (Interactive Voice Response) and CTI (Computer Telephony Integration) applications.
We wouldn’t simply praise Leo’s voice in this way without providing evidence. Check out Leo’s voice for yourself to understand the excitement we are expressing! Leo can also be put to work by choosing his voice and entering whatever text you want him to speak in the demo part of our home page!
And who is Beth?
Beth is our fourth female and sixth overall US English voice. Beth is an American English text to speech voice. As a result, our customers have a huge selection to choose the ideal English voice for their applications.
Her voice has an alluring and comforting tone, which is what makes Beth unique. Synthesized speech frequently lacks these characteristics, but Beth’s voice unquestionably has the capacity to engage her listeners.
Beth’s voice is perfect for personal usage, as well as for use in education, language acquisition, screen reading, health monitors, and medical equipment.
Once more, we wouldn’t make all of these statements without supporting them. By choosing Beth’s voice in the demo part of our home page, you may hear her voice for yourself and have her read any text you input.
How are these voices able to seem so lifelike?
You’ve probably heard the saying “slow and steady wins the race.” That is the method we employ while creating our speech engines. We employ the USS technique, which takes much longer but currently produces the best voice quality, as we detailed in our blog post “HTS VS. USS: WHICH SPEECH SYNTHESIS TECHNIQUE IS BETTER.”
By employing this method, it takes us almost a full year of arduous work from beginning to end, but the greater quality of our voices makes the effort worth it to us! We believe that after you use our text-to-speech technology, you’ll agree.
Can more voices soon be heard?
Of course! By including new languages, we are growing our line. In order to give you even more versatility, we’re now adding voices to the languages we already support. We’re working incredibly hard to maintain our position as the top supplier of text-to-speech technology, and we can’t wait to show you our new voices—or, even better, to have our new voices show you who they are—to you!
How do you feel?
Did you pay attention to Beth or Leo’s voices? How do you feel about them? What kinds of tools or programs would you wish to use to hear these voices? Comment below and let us know!