Vulpine

Voice runtimeSelf-hosted

Give your agent a voice. Keep it in the house.

You already run an agent. Vulpine lets you talk to it. It hears you and answers simple requests at once. It sends everything else to your agent, then speaks the reply in a voice you chose. It runs on a Mac in your house, with apps for your screens and speakers for your rooms.

Install it See how fast it answers

Speech in
on your Mac
Voice out
on your Mac
Simple requests
answered at once
Agent
Pi today, more to come
Account
none

VulpiListening

Vulpi, the Vulpine fox, drawn as a screen of dots: a cybernetic fox sitting with its tail curled, listening.

Move over the fox, or tap it. A ripple leaves from its ear.

01 / The turn

Two ways to answer.

A turn is one request and its reply. The gateway is the Vulpine program on your Mac. It answers simple requests itself, at once. It sends everything else to your agent, and only those turns wait.

Is it a verb?

A verb is a request the gateway can do by itself.

  1. YesThe gateway does it

    0.1 s to its first word

  2. NoIt goes to your agent

    1.9 s to its first word

The bars are to scale. Each bar starts when the gateway is sure you have finished. That wait is about 1.0 s on both ways. Each time is a median, the middle value, of live turns on a home Mac. The short bar is two measured pieces laid end to end, because no verb turn has been timed whole yet.

Yes, a verb

The gateway does it.

The gateway knows a short, fixed list of requests. It does them itself, and your agent is not asked.

  • turn off the office lightsThe lights go off, and it says what changed.
  • say that againIt repeats its last reply.
  • pull up retro weather on the screenIt shows that page on the screen.
  • never mindIt drops the request. Nothing is sent.
  • start overThe conversation starts again from nothing.

No, anything else

It goes to your agent.

Questions, plans and open requests. The gateway sends your words to your agent, and your agent uses its tools.

  • any weather warnings?Your agent looks them up and tells you.
  • play jazz radio in the kitchenYour agent finds a station and plays it there.
  • what's on my screenYour agent reads the screen and tells you.
  • what's this errorYour agent reads the error and explains it.
  • I'm in the kitchenYour agent notes which room you are in.
Each step, its time and its receipt

A receipt is a measurement file saved beside the code. The receipts call your agent the brain, and its first word a token. The commit is the moment the gateway is sure you have finished.

  1. AFinishat home

    978 ms

    from the end of your speech to the turn's commit; both paths wait for it

    Speech end to commit on the home Mac: the median of 218 live turns, 29 October to 6 November.

    Receipt, 2026-11-06: brain-ttft-cloud-vs-local-2026-11-06.json

  2. BMatchat home

    8.6 µs

    for the gateway to recognise one of its own verbs at the commit

    The phrase match the commit runs, per call, over 80,000 calls in an unoptimized build: an upper bound.

    Receipt, 2026-11-07: page-verb-cost-20261107.md

  3. CSpeakat home

    140 ms

    from text to the first audio, when the voice has been quiet for up to a minute

    The voice worker's time to first audio on the home Mac after 5 seconds to 1 minute of quiet: the median of 457 live requests. It is quicker when it has just spoken and slower after an hour of silence.

    Receipt, 2026-11-07: tts-idle-ttfa-2026-11-07.json

  4. DThinkaway

    1.4 s

    from the commit to a hosted brain's first token, the one leg that leaves the house

    Commit to first token with a hosted model: the median of 218 live turns, 29 October to 6 November.

    Receipt, 2026-11-06: brain-ttft-cloud-vs-local-2026-11-06.json

  5. ESpeakat home

    441 ms

    from the brain's first token to the first audio of the reply

    First token to the first audio chunk: the median of the same 218 live turns.

    Receipt, 2026-11-06: brain-ttft-cloud-vs-local-2026-11-06.json

What these numbers do and do not say

Read it honestly. Each step on the agent way is a median over the same live turns. But medians of steps do not add up to a median turn. Traced whole, an agent turn takes 3.0 s from the end of your speech until you hear the reply. One turn in ten waits 3.8 s or more for the agent's first word. No verb turn has been timed whole yet. Some verbs answer with an action or a panel, not a sentence.

The short way is the small one today. In one week of live turns, 14 of 230 were verbs (6 in a hundred). The rest went to your agent. After the commit, a verb answers about 13 times sooner. Your agent does not wait idle. On 117 of 229 turns, the gateway started it before you finished speaking. That is the early start.

The long step is the model. Today the supported agent runtime is Pi, installed on your Mac. More runtimes are to come. The model your agent calls is usually a hosted one, and that call is the one step that leaves the house. A model on your own Mac has no live turn timed, so no number is claimed for it. How the install guide sets Pi up

Every step has a budget. A change that adds time to one step must name the step that gives the time back. That rule is the turn budget.

Where the decision model sits

Beside the turn, not on it. The decision model is a small model on the home Mac. The gateway asks it three questions while you speak: was that for Vulpine, have you finished, and which verb. Its answer takes 682 ms, and the turn never waits for it. Today the gateway matches verbs from its own list. The model can do one thing: drop a follow-up that was not meant for Vulpine. That is the drop gate. Its next job is to send more turns down the short way. It is being measured for that job under the decision contract.

02 / One hub

One hub. Six lanes.

Most assistants are a chain. One service calls the next, and each hop adds delay. Vulpine puts one gateway in the middle, on a computer in your house. Each lane is one job, such as listening or speaking. Watch four events go round the hub. Each one takes its own route.

macOS the desktop app Web any browser Speaker a room speaker iOS in development Screens and speakers Rooms speakers, presence Home verbs out, events in Cameras events in Fleet agents on your machines The house Listen Turn-taking Decide Think Act Speak Now: A verb turn Now: An agent turn Now: A camera event tests refactor review docs Now: A fleet task
Going round the hub

A verb turn

You say “Turn off the office lights.”

  1. Listen You speak to a room speaker. Your words become text.
  2. Turn-taking You stop. The gateway is sure you have finished. 978 ms
  3. Decide It is a verb the gateway knows. Your agent is not asked. 8.6 µs
  4. Act The gateway runs it through the home adapter.
  5. Speak It says what changed. 140 ms

An agent turn

You say “What is the weather tomorrow?”

  1. Listen You ask from the desktop app. Your words become text.
  2. Think, early Your words so far hold steady. The gateway starts your agent early and holds its reply back.
  3. Turn-taking You stop. The gateway is sure you have finished. 978 ms
  4. Decide No verb matches. The turn goes to your agent.
  5. Think Your agent's first word arrives. 1.4 s
  6. Speak The gateway speaks the reply. 441 ms

A camera event

In the house Someone is at the door.

  1. Act A camera sees someone. The event comes in through an adapter.
  2. Act Room presence says which room you are in.
  3. Speak The announcement plays on that room's speaker.

A fleet task

You say “Run the tests, and write the docs.”

  1. Listen You hand out work. Your words become text.
  2. Turn-taking You stop. The gateway is sure you have finished.
  3. Decide No verb matches. The turn goes to your agent.
  4. Think Your agent plans the work.
  5. Act The fleet grows. Coding agents start on your machines.
  6. Act They finish, and their reports come back.
  7. Speak It tells you what is done.

Screens and speakers

  • macOS the desktop app
  • Web any browser
  • Speaker a room speaker
  • iOS in development

The house

  • Rooms speakers, presence
  • Home verbs out, events in
  • Cameras events in
  • Fleet agents on your machines
The six lanes and the hardpoints on each
  • Listen

    The gateway hears the wake word. Then your speech becomes text, a few words at a time.

    wakestt counted in speech_end_to_commit, on your machines

  • Turn-taking

    Have you finished? The gateway waits for the pause after your request. Then it is sure.

    answered by decision, mounted on Decide counted in speech_end_to_commit, on your machines

  • Decide

    Is it a verb the gateway runs itself? Then your agent is not asked. Anything else goes to your agent.

    decision counted in speech_end_to_commit, on your machines

  • Think

    Your agent, with its memory and what it can look up. Today the supported agent runtime is Pi, installed on your Mac. More runtimes are to come. It gets the text of a turn, never the audio.

    brainmemoryretrieval counted in commit_to_first_text, on your Mac (its model can be hosted)

  • Act

    Verbs go out to the house through adapters. Events come in the same way. Each action returns a result.

    room counted in tool_round, adapters beside the hub

  • Speak

    The reply becomes audio in the voice you chose.

    ttsvoice counted in first_text_to_first_audio, on your machines

A hardpoint is a named slot for one part you can swap. Nine hardpoints mount on the hub's lanes. The other two, avatar and render, mount on each screen. The loop is slowed down so you can read it. It is not to scale.

03 / Within reach

The house within reach.

Rooms, lamps, cameras and your other machines reach the hub through adapters. An adapter is a small program that connects one kind of device. Screens and speakers connect to the hub directly. Your agent runs on your Mac. The model it calls is the one part that can sit outside the house, on the dashed line.

Four things that happen
Your house Outside Model the one your agent calls

04 / Hardpoints

Every part is a slot.

To start, bring a Mac with Apple silicon and the agent you already run. Today the supported agent runtime is Pi, installed on that Mac. More runtimes are to come.

The install downloads the rest: speech recognition (about 630 MB) and the voice (about 1.3 GB). There is no server to stand up and nothing else to bring. What an install needs

A hardpoint is a named slot for one part. You can swap the part that is included for your own. 2 slots take a swap today: speech to text and text to speech. The other slots have their names, and their swaps come next.

05 / Surfaces

Where you talk to it.

06 / Not included

What is not in the box.

  • No cloud account

    Nothing to sign up for. It runs on a computer in your house.

  • No always-on upload

    Your machines process the audio. Your agent gets the text of a request, never a live microphone stream.

  • No advertising

    Nothing is sold, and nobody builds a profile of you.

What stays at home, and what your agent sees

07 / Install

Install it in four steps.

There is no account and no price. You host Vulpine yourself, and nothing is sold. The source is not public yet. You can check what you need and read the install guide now.

  • Needed

    A Mac with Apple silicon

    It needs 16 GB of memory, and about 7 GB free for the install, plus room to build the gateway.

  • Needed

    Pi, installed on that Mac

    Today Pi is the supported agent runtime. More runtimes are to come.

  • Optional

    A speaker for a room

    A small puck with a microphone. It hears the wake word itself.

  • Optional

    A screen for a face

    Vulpine.app on the desktop, or a browser tab.

  1. Check the Mac

    Check memory, disk and macOS before you install anything. Before you start

  2. Install the tools

    By hand, once: Apple's command line tools, mise, cmake and ffmpeg, and Pi.

  3. Run the install

    One command builds the gateway, writes its settings and downloads the voice. Speech recognition and the permissions helper are two more steps by hand today. The install sequence

  4. Let the doctor finish

    The doctor is the last step. It checks every part and names the fix for anything missing. The install guide

08 / Questions

Common questions.

What do I need to run it?

A Mac with Apple silicon in your house, and an agent. Today the supported agent runtime is Pi, installed on that Mac. More runtimes are to come. The install guide starts with a few tools you add by hand. Then one command builds the gateway, writes its settings and downloads the voice, and two short steps by hand follow it. The guide ends with a doctor that checks every part and names the fix for anything missing. Install

Does my audio leave the house?

No. Your own machine turns your speech into text, and it makes the voice too. Household audio never leaves your machines. A check on every change to the source refuses a command that would copy audio anywhere else. Why speech stays home

What does my agent see?

The text of a turn that needs it, never the audio. Your agent runs on your Mac. Today that is Pi, installed there, with more runtimes to come. The model it calls is usually a hosted one. Speech recognition and the voice stay on your machine. What the model sees

How does it know I am talking to it?

Today, by a wake word and the pause after your request. A small decision model on your Mac is also asked three things: were you talking to it, did you finish, and what did you mean. It can already drop a follow-up that was not meant for it. The rest of what it answers is recorded and routes nothing yet. The decision contract

Does it know who is speaking?

It can compare a voice with the voice you enrolled. It only records the result. The gate that would act on the result is off by default, so it refuses nobody. Voice commands

Does it read my mood?

Only if you opt in. Every part is off by default. When it is on, signs that a turn went wrong can make the next reply shorter or more careful. It never says how you sound, and its notes stay on the home machine. The mood decision

Where do the numbers on this page come from?

From measurements saved beside the code. The page reads them when it is built. The build fails if someone types a number in by hand. How the site is built

Can I see what it is doing?

Yes. Vulpine Gateway.app shows sessions, speech, your agent, the house and the approvals. It reads the gateway over a local connection that only your account can open. The Gateway window