Voice agents should become more than transcription tools. Instead of simply turning speech into text, they should understand what users are trying to achieve. The same spoken idea may need to become a short Slack message, a detailed email, a technical issue, or a personal note. A useful voice agent should adapt automatically.
This is the direction Loqua is exploring: voice as an intelligent layer across the apps people already use. It can understand the current application, nearby content, personal vocabulary, and writing style, then shape spoken thoughts into something ready to use. Users should be able to speak naturally without organizing every sentence beforehand.
The next step is real-time duplex conversation. A good agent should know when someone has finished speaking, when they are only pausing, and when they want to interrupt. It should also recognize signals beyond words, such as emotion, hesitation, emphasis, and tone. Its own voice should feel equally natural, expressive, and appropriate to the situation.
Behind this conversation, the agent needs deeper capabilities. It should remember relevant context, think through difficult requests, use tools, and continue working after the conversation moves on. The voice experience remains fast and fluid, while more complex reasoning happens quietly in the background.
We all know that long-horizon coding tasks are difficult, but understanding long, multi-turn conversations is even harder. The agent must remain consistent, respond with the right emotion, use tools correctly, and remember what matters.
The screenshot feature is such a natural interaction. Instead of explaining what you're looking at, you just show it.
Loqua
@mia_qiao Exactly! Sometimes showing the screen is way easier than describing what's on it.
Loqua
@mia_qiao This is our ultimate goal by designing the multimodel LLMs, to keep all context in a single model makes everything to next level!
My biggest bottleneck isn't typing speed. It's getting thoughts out of my head before they disappear.
Loqua
@antler_kaku This is a huge part of why we built Loqua! Speaking is often much closer to the speed of thinking.
Loqua
@antler_kaku Exactly! New features coming soon, stay tuned!
This is a really cool product, so many voice AI tools at the moment really don't work well, I've been looking for something to really help use AI voice in my day to day work!
Loqua
@tony_lewis1 Really appreciate that 🙏 That’s exactly what we’re hoping for: not voice as a novelty, but something you can actually keep using throughout a normal workday. Would love to hear which workflows you end up using it for most.
Loqua
@tony_lewis1 Hey Tony, we will keep improving our models and user experiences, give us feedbacks, and stay tuned for more features!
Sheet0
WOW, I like AI assistants more when I can clearly see when they're doing something versus just listening!!!
Loqua
@wenwei_zhang Same here! Seeing the action happen makes the whole interaction feel much more trustworthy — especially when it’s doing something on your behalf instead of just generating text. We’ve been thinking a lot about making that feedback really clear.
Loqua
@wenwei_zhang It's getting there. The next generation voice agents see, listen and get things done, with memories and full hands of tools!
Video Roll
I always avoided voice typing because I ended up spending more time fixing the output afterwards.
Loqua
@gxy5202 That's the exact problem we were trying to solve. The goal isn't faster transcription if you still have to rewrite everything.
Loqua
@gxy5202 I feel the pain through my working career. Last generation ASR did not meet the general needs of daily work, however new generation speech recognition with MLLMs pretty much solved the problem, give it a try!
Ever since my personal "AI"—my newborn son—arrived, my hands have been completely tied up.
As a strategy engineer, I needed a way to keep working with zero hands, so I started turning my daily workflows into quick voice commands. It turned out a few of us on the team had been thinking about the same problem, and things just clicked from there.
By the way, this entire post was written with loqua—the boss was crying, keyboard wasn't an option.
So please, don't worry about "bothering" me with too many questions! My hands are busy holding the baby, but replying to your comments takes zero effort now.
This feels closer to having an AI assistant next to you rather than another text box to type into.
Loqua
@qi_xiao2 That's pretty much the direction we're going for😄 less typing, more just talking to your computer.