YouTube video by LARRUZ (March 14, 2025) discussing innovations in text-to-speech. The speaker introduces new entrants—HUME AI's Octave TTS and Sesame—and focuses on Octave's claimed ability to 'understand' text to vary prosody (intonation, pacing, emphasis) according to content examples (e.g., whispered vs. angry 'Are you serious?'). The segment argues this capability shows further growth potential for voice assistants.
We have some innovations from our text to speech, aka voice assistant category. So for a long time, OpenAI has been leading the pack here with their advanced voice mode. And now we have two more. We have HUME AI and we have Sesame. So let's start with the HUME release here. They call it Octave Text to Speech. It's another text to speech model, but it has one major difference. This one actually understands what it's saying. Now, believe it or not, this is not a feature that most of these models have. If you just give it some text, it will read it in the voice it has and that's it. It will not pay attention to the content of it and use things like intonation or pacing to enhance the message based on what's in it. So as you can see, the phrase, are you serious? If you're whispering it, it should sound like this, Are you serious? And if you're saying it in an angry and furious manner, are you serious? Different story. This text that is written in all caps obviously should be a bit more aggressive. Oh, no, not me, mate. All right, okay. I think you see the point. And I thought this was super interesting as this kind of shows that there is a lot of room for these voice assistants to grow.
