Send a meeting link to a Telegram bot. Tekki shows up in the Meet as its own participant, listens, thinks about it, and answers out loud with a face that reacts. Ollama does the thinking, whisper the listening, Kokoro the voice — all of it local.
Free & open sourceNothing leaves the machineMac or Linux
…so are we shipping the migration this week?
How it gets in
To be in a video call you need to be two devices: a camera and a microphone. Everything else is detail. The AI half is commodity — the device half is where the work is.
Chrome plays the meeting into a sink that isn't a speaker. One parec records its monitor — every participant mixed for free.
The monitor stream becomes text on the host, where it keeps its GPU acceleration. Base English model, no timestamps.
A small non-reasoning model answers in a third of a second and tags its own expression inline, e.g. [thinking].
The reply becomes PCM through mlx-audio — a voice that doesn't sound like a satnav — and its amplitude drives the mouth.
The avatar is drawn into a canvas at about a millisecond a frame, then handed to Meet as a camera track.
Patched before Meet's own JavaScript runs. Meet enumerates a camera and a microphone and cannot tell they aren't hardware.
Chrome routes decoded remote audio to the output device and never hands it back to WebAudio, so intercepting tracks in the page is a dead end — it attaches happily and delivers silence. Recording the sink monitor instead also means Tekki can't hear itself: its voice leaves by the microphone track and never reaches a speaker.
Measured over the same three turns: qwen3:4b took 23s to answer cold, then returned empty replies at 38s and 40s. On a reasoning model the token budget covers the scratchpad first, so a cap sized for two spoken sentences gets spent thinking.
| turn | qwen3:4b | 3B, no reasoning |
|---|---|---|
| first, cold | 23.4s | 10.1s |
| second | 38.1s · empty | 0.32s |
| third | 40.8s · empty | 0.32s |
The face
Not to save effort, and not as a placeholder for something photoreal later.
Anyone glancing at the call can see there's a bot in it. That's a promise the consent section makes, and an antenna is what keeps it.
Any face implies an age, a gender and an ethnicity, and every viewer reads something into those. A robot sidesteps the question entirely.
A drawing that blinks and reacts reads as charming. A nearly-human face that blinks slightly wrong reads as a corpse.
And it stays cheap — arcs and rounded rectangles, about a millisecond a frame, where a diffusion model needs hundreds. That's the whole reason local realtime is possible at all.
Every tile is the live renderer, not a recording — the same drawAvatar that feeds the camera track in a call.
~1ms / frameThe remote control
A supervisor process takes the message and forks a join session per call, so several chats can each hold their own meeting — one call per Google account.
tekki_bot
online · local
/start
Ready. Send me a Meet link.
meet.google.com/xyz-abcd-efg
Knocking. Admit me and I'll turn the camera on.
/say sorry, I was on mute
Said it. 4 people in the call, listening.
Try it
Needs Docker, and a Mac or Linux box with enough memory to hold a 3B model. No account to create, no key to buy, no endpoint to trust.
Ollama for the thinking, whisper for the listening, Kokoro for the voice.
ollama pull llama3.2:3bbrew install whisper-cppmkdir -p models && curl -L -o models/ggml-base.en.bin \ https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-base.en.bin # Kokoro, for a voice that doesn't sound like a satnavuv venv --python 3.12 .venvuv pip install --python .venv/bin/python mlx-audio "misaki[en]" fastapi uvicornThey stay on the host, not in the container, so they keep their GPU acceleration.
ollama servewhisper-server --model models/ggml-base.en.bin --port 8178 --host 127.0.0.1 --no-timestamps.venv/bin/python tools/kokoro_server.py --port 8179Use a throwaway — it appears in calls under that account's name. Nothing in the repo reads, stores or transmits a password.
cd bot && ./signin.sh # opens a browser at localhost:6080; sign in by handTalk to @BotFather, send /newbot, and put the token in bot/.env.
TELEGRAM_TOKEN=123456789:AA...Message your bot /start, then send it a Meet link. Admit it when it knocks.
cd bot && docker compose upHonest section
Somebody has to admit it.
No diarisation — everyone is one voice to it.
Screen shares, slides and faces are all invisible.
Google refuses automated anonymous clients, so it needs its own account.
OAuth grants API scopes; there is no Meet API for joining a call as somebody else. That door doesn't exist.
It answers everything it hears, which is fine one-to-one and rude in a group.
Consent
Tekki joins under its own name, renders as an obvious cartoon robot, and doesn't attempt to look human. Anyone can see there's a bot in the call. Any feature that made it harder to notice would be the wrong feature.
Also in the repo
SwiftUI, putting the avatar in a window for OBS to capture and speaking through BlackHole. It works, and it's how the avatar, brain and voice were built — but becoming a device inside the page removed two prerequisites and all the manual setup.
swift run understudy-window
swift run understudy-brain
swift run understudy-renderClone it, pull a 3B model, and message a bot a link. Everything it hears stays on the machine it runs on.