# Where your voice goes

> What happens to the sound of your voice, hop by hop, and which parts never leave the device.

Source: https://docs.thalovant.com/trust/

---
This page follows one spoken sentence from your mouth to the answer, and says
what happens to it at each hop. It describes what the shipped software does.
Where a hop depends on something you chose, it says so instead of guessing on
your behalf.

## What Leaves The Device

**The wake word never leaves the device.** Detection runs locally, on a model
that ships inside the app. Nothing is sent anywhere while a device waits for
"Hey Jarvis" — that's the whole point of a wake word.

**From the phone app, the hub receives text, not audio.** The sound of your
voice becomes words on the phone; the words travel to the hub. The hub answers
with text, and the phone speaks it. On other clients this depends on the speech
plugins installed there — see below.

**The link to the hub is encrypted.** Client and hub authenticate each other
before anything is sent; the client records the hub's identity on first contact
and checks it on every later connection, so a changed hub is an error rather
than a silent redirect.

## Hop by Hop, on the Phone

1. **Waiting.** The microphone feeds a local wake-word model bundled in the
   app. Audio is examined in 80 ms frames and discarded. It isn't written to
   storage, and it isn't sent anywhere.

2. **Woken.** Once the wake word is confirmed, the app asks Android to turn
   the next sentence into text.

   The app **asks for offline recognition first**. If your phone has the
   offline model for the language you're using, the sound never leaves the
   phone.

   If it doesn't have that model, the app falls back to your phone's online
   recogniser — so for that sentence, audio goes to whoever provides speech
   recognition on your phone, usually its manufacturer or Google. **That hop is
   between you and your phone's vendor. Thalovant isn't in it and never
   receives the audio.**

3. **Asking.** The recognised **text** goes to your hub over the encrypted
   link. Audio never does.

4. **Answering.** The hub replies with text. The phone speaks it using the
   phone's own text-to-speech voice. Generating the sound is local.

  To keep every sentence on the phone, install your language's offline speech
  recognition in Android's settings. The app prefers it whenever it's there.

## Hop by Hop, on a Speaker or a Computer

Thalovant Voice, the client for rooms and appliances, detects the wake word
locally in the same way. What it does next depends on the speech plugins
installed on that machine: both recognition and the voice are pluggable, and
the default resolves to whatever is installed rather than to a fixed service.

**So this hop is yours to know.** Check which plugins are configured on that
machine before assuming audio stays on it.

Thalovant Voice can also retain recordings for debugging, and **doesn't
by default** — retention happens only when you set a capture directory.

## What the Hub Keeps

The setup guides connect your client to a Thalovant-hosted hub. Installing a
client on your own device does not move that hub into your home. See
[hosted hubs and local devices](/start/hosted-and-local/) for that distinction
and the limits of offline speech processing.

Conversation context and saved memory depend on the hub, its skills, and the
workspace. Public Daily Desk's connected-client chat, the anonymous browser
preview, and private-workspace memory are different paths. Check
[public hubs](/workspace/public-hubs/) and [memory](/workspace/memory/) for the
behaviour of the path you use. Local wake-word detection does not mean that all
processing or storage stays on your device.

## Check Hosted-Service Policies

For published service policies, read the [Privacy Policy](https://thalovant.com/privacy/),
[subprocessor list](https://thalovant.com/subprocessors/), and
[legal documents](/legal/). This technical description does not establish
retention periods or data-residency guarantees.

If a policy is marked as a draft or pending review, ask
[support](/account/get-support/) to confirm the applicable policy before
relying on a commitment. Ask about your workspace's retention and residency
requirements explicitly rather than inferring them from local speech processing.