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.
Buffup.AI
most voice tools fail badly when dictating terminal commands or nested JSON structures. am curious if your underlying model treats code syntax natively or if i still have to manually edit brackets later.
Loqua
@sansa_grey Great question, for exact terminal commands or heavily nested JSON, I wouldn’t claim perfect syntax-level accuracy yet. Those cases are much less forgiving than normal prose, since one bracket or character can matter.
Loqua is already useful around coding workflows and technical explanations, but for dense structured code we’d still recommend reviewing the output. Improving this is definitely an area we care about.
Loqua
@sansa_grey That is the way we are aiming to, a truly hands free coding experience. Try variable names, terms, complex logic together with CC & Codex, it reads coding context so all the dictation feels much better. We will keep improving the model for better performance!
The screen-awareness feature sounds really useful. Being able to explain what’s on screen without switching between apps could make work much smoother.
Loqua
@jharkhandi_chora1 That’s exactly the friction we wanted to remove. A lot of the time, explaining the context to AI takes longer than the actual question 😅
Being able to just show what you’re looking at and ask directly feels much more natural.
Driven
Screenshot to ask is such a simple idea but removes so much friction. No more explaining screenshots manually.
Loqua
@zaniaz Yep. Just capture what you're looking at and ask about it directly.
This is probably perfect for those “wait, I just had an idea” moments
Loqua
@eren_mindful Exactly! Our team member and many users use it as notebooks for random thoughts, especially for young parents who work and attend baby at the same time.
Expertise AI
The screen context part is what caught my attention. Being able to just point at something and ask instead of explaining what I’m looking at every time sounds genuinely useful. Curious to try this in my daily workflow!
Congrats on the launch! 🚀 Context switching and formatting messy thoughts are huge friction points in daily workflows. Excited to try out the screen-reading feature alongside voice dictation best of luck today!
Loqua
@elias_leo1 Thanks so much! 🙏 Those little interruptions add up way more than you realize until you start removing them 😅
Really curious to hear how screen context + dictation fits into your workflow once you’ve had a chance to try it.