SayOVA: AI Voice Assistant

SayOVA — your Orb Voice Assistant — turns your Wear OS watch into a real conversation partner. Raise your wrist, talk naturally, interrupt whenever you like — and hear the answer while you read it along on your watch.

Real conversations, not commands
SayOVA streams your voice live to a speech-to-speech model — Google Gemini Live or OpenAI Realtime — and plays the answer as it is generated. Speak over it to interrupt, just like with a person, or tap the orb.

Hear it and read it
Both sides of the conversation appear on the screen as you talk. The part of the answer you have already heard is bright, the rest is still dim, so you never lose your place.

Your interpreter on the wrist
Pick two of 21 languages and hold the watch between you and the person you are talking to. SayOVA says everything in the other language and shows both sides as text.

Quiet when it has to be
In a lecture, a meeting or a quiet room? One tap switches SayOVA's voice off and the answers appear as text.

Gets things done
Ask SayOVA to set a timer or an alarm (every weekday, if you like), save a note, check the battery — or search the web for news, weather, opening hours and anything else that is current.

Prepares things on your phone
"Text Lena on WhatsApp that I'm ten minutes late", "Put the dentist on Tuesday at three in my calendar", "Route to the station on foot" — SayOVA reads the message back, and after your yes it waits on your phone in your own apps, ready for you to send, add or start. SayOVA never sends anything in your name.

Knows your watch — when you ask
"What's the weather here?", "What's my heart rate?", "How many steps today?", "What's on this afternoon?", "When does my alarm ring?", "Pause the music", "Call Lena", "Open the flashlight" — SayOVA uses your location, the weather, heart rate, steps, calendar, air pressure, next alarm, music, contacts, apps or notifications only for that question, after you allowed it once, and shows an icon while it does. Calls are placed only after you confirmed name and number.

Remembers what you ask it to
Say "Remember that I'm vegetarian" and every later conversation knows. Only what you ask for is kept, on the watch, and you can read or delete every fact in the settings.

Your provider, your key, your data
SayOVA works with your own API key from Google Gemini (from about a cent a minute; a free tier is available) or OpenAI. Your voice goes straight from the watch to the provider — there is no SayOVA server in between, no account, no tracking and no ads.

Hear it first
Before you set anything up, SayOVA plays a sample conversation on your watch, both sides spoken. A short tour shows the rest.

Setup in a minute
Scan the QR code on your watch with your phone, paste your key, compare a six-digit code, done. The key is encrypted in your browser for your watch alone — no companion app, no typing on a tiny keyboard.

Made for the watch
• Uses Wi-Fi or LTE during a conversation for smooth audio
• Keeps talking with the screen off, with an icon on the watch face
• Tile and complication to start talking with one tap
• Works with Bluetooth headphones
• Personalities (friendly, concise, detailed, tutor, language partner or your own), 40 voices to listen to before you choose, answer language
• Running cost estimate, usage statistics and a monthly budget
• History stored only on the watch, for as long as you choose

Open source
SayOVA is open source under the Apache License 2.0. You can read exactly what it does with your voice and your key: github.com/DevEmperor/SayOVA — and every function is explained step by step, with pictures, in the guide: github.com/DevEmperor/SayOVA/wiki

Requires a Wear OS 3 or newer watch with a microphone and an API key from Google Gemini or OpenAI. Usage is billed by your provider. The Gemini API is for users aged 18 and over.