AI voice is suddenly getting way more serious, so I tested the new wave of voice models from OpenAI, Google, Inworld, and Grok to see what actually feels useful. OpenAI’s GPT Realtime 2 is fast and way more natural for voice agents, but I also ran into hallucinations and instruction-following weirdness. Inworld TTS-2 is incredibly quick, while Google’s Gemini TTS preview gave me some of the most expressive AI voice reads I’ve heard yet. The big question is whether voice AI is finally becoming something worth using every day.
MattVidPro Discord:
Follow Me on Twitter:
Buy me a Coffee!
▼ Extra Links of Interest:
General AI Playlist:
Instagram: instagram.com/mattvidpro
Tiktok: tiktok.com/@mattvidpro
Gaming & Extras Channel:
Let’s work together!
– For brand & sponsorship inquiries:
– For all other business inquiries: [email protected]
Thanks for watching MattVideoProductions! I make all sorts of videos here on Youtube! Technology, Tutorials, and Reviews! Enjoy Your stay here.
All Suggestions, Thoughts And Comments Are Greatly Appreciated
source
