Need help?
Search first: someone may have asked already. If you are still stuck, ask the community.
Announcements
View allWelcome, new members! Start here
A short tour: categories on the left, Home for the highlights. Introduce yourself in General, ask in Help & Support, and show what you built in Show & Tell. Be kind, be specific.
Read more- Community guidelines (please read)
Be kind and stay on topic. No spam or hard selling. Say what you tried when you ask for help. Moderators may hide posts that break these rules, and we always e…
6 - XIRO 4.3 is rolling out: faster wake word, calmer HUD
XIRO 4.3 is rolling out in waves today. - The wake word reacts noticeably faster - A calmer Night face on the HUD - Fewer permission prompts for actions you al…
4
General
View all- Working from home with an AI assistant: has it changed your day?
I take fewer breaks to switch tabs and more breaks to actually rest.
4 - Show of hands: who types less than before?
I dictate emails, notes and messages now. My wrists thank me 🙏
5 - Using XIRO with a screen reader: tips and rough edges
Blind developer here. Happy to share what works and what does not.
31
Feature Ideas
View all- Voice cloning of my own voice, locally
I want replies in my own voice for voice notes, with nothing leaving the PC.
4 - A community store for workflows
Share and install routines in one click, with a permission preview.
4 - Proactive reminders: let XIRO nudge me before meetings
A gentle 'your call starts in ten minutes, want the notes?' would be perfect.
5
Show & Tell
View all- Healthcare data and local models: red lines
Where is local fine, and where does regulation still bite?
4 - Voice-driven Blender shortcuts for 3D artists
'Add a bevel' and 'frame selected' by voice while my hands stay on the tablet.
4 - My desk: XIRO on a second monitor as an always-on HUD 📸
Ten-inch monitor, HUD in full screen, calendar on the left. Happy to share the layout.
4
Future of Voice AI
View all- Education with a patient AI tutor: promise and risks
Infinite patience and personalisation, but also shortcuts and errors.
4 - Emotion-aware replies: calm voice when I sound stressed
Prosody carries a lot of information. Use it, gently.
12 - Open-source models vs closed models: who wins voice?
Closed leads today. Open is closing the gap and respects privacy.
12
AI Developers
View all- Streaming ASR: Whisper variants vs newer models for real time
What are you running for sub-second partial transcripts, and on what hardware?
4 - Testing voice apps: how to automate regression tests
Recorded audio fixtures plus intent assertions?
4 - Safe actions: a permissions model for an assistant that clicks things
Scopes, previews and undo. How far should defaults go?
4
Voice & Languages
View all- Urdu and English in one sentence: how well does dictation cope?
'Kal meeting hai at 3 pm, please remind me.' This is how we talk.
8 - What would make you recommend XIRO to a friend?
Mine would be: it just works on the first day. What is your bar?
32 - Indonesian and Javanese: regional speech support
Many families speak both. Plans?
18
Privacy & Local AI
View all- Healthcare data and local models: red lines
Where is local fine, and where does regulation still bite?
4 - A community store for workflows
Share and install routines in one click, with a permission preview.
4 - GDPR and voice assistants: what should a small business do?
Lawful basis, retention, and the right to delete.
4
Business & Big Ideas
View all- Where is the next billion-dollar voice AI startup hiding?
My guess: a boring vertical with a painful phone problem.
4 - Why do big-tech assistants feel stuck?
Huge reach, but they feel the same as five years ago.
4 - Insurance, banking, telecom: who adopts voice agents first?
Compliance slows everything but the volume is enormous.
4