This story has been published on the elocance blog. Check it out!
TTS stands for text-to-speech which refers to synthetic (non-human) voices reading text out loud. You’re probably already familiar with Alexa, Siri, Watson, Polly, etc. While they’ve been the stars of the text to speech revolution, there are other, smaller but, extremely impressive, players with game-changing technology. Here’s who we’re excited about:
Why they’re cool: They’re creating personalities, not just voices. These personalities correspond to specific uses and occasions. They are targeting brands that want to decrease their voice over recording costs by using synthetic voices.
Check out their voices:: https://www.youtube.com/watch?v=evmvsviHNYY
Why they’re cool: Lyrebird is also focused on content creators but is enabling individuals to create their own, personalized synthetic voice. Using artificial intelligence, they’ve created a studio that makes creating your own voice avatar accessible.
Create your own voice: https://www.descript.com/lyrebird-ai
Why they’re cool: Dessa’s recently developed AI model is capable of creating a synthetic voice that replicates real, human voices. They’ve even created a synthetic voice for Joe Rogan, the popular podcast host.
Why they’re cool: DeepZen’s voices are pushing the envelope when it comes to emotion and expression. They partner with various sectors from publishing and advertising to gaming which all require human emotion for audio communication.
Test the voices: http://deepzen.io/
As artificial intelligence and synthetic voice technologies improve, it’s clear that audio and its applications will continue to expand. As an app that aims to use the best existing synthetic voices, we continue to stay tuned to how we can make listening for personal and professional development, as enjoyable as possible.
The elocance Team
elocance is your audio superpower. Build productive habits and save time by listening. Save articles and PDFs etc., turn them to audio and learn on the go.