Local AI · Voice Mode

Talk to your model. Nothing leaves the room.

Voice Mode gives LumaBrowser a spoken conversation loop where both halves run on your own machine. Whisper listens, your local model thinks, and a neural voice answers out loud. There is no cloud speech service in the path, no GPU requirement, and no recording of your microphone anywhere off the computer.

Download LumaBrowser - free See where the audio goes
Windows and Linux · no GPU needed · no audio uploaded

How a spoken turn works

Click the microphone button in the chat composer and the loop starts. From there it is hands-free: the browser decides when you have finished speaking, transcribes, answers, and listens again.

It hears you start

A local voice detector watches the microphone and adapts to the room's noise floor, so it triggers on speech rather than on a fan or a keyboard.

It keeps your first words

A rolling one second buffer sits in front of the detector, so the beginning of your sentence is never clipped off while it decides you were talking.

It knows when you stop

After a short pause the utterance is closed and sent to transcription. Very short blips and known silence artefacts are discarded rather than sent to the model.

You see it as you speak

A live transcript bubble above the composer updates while you talk, so you can tell it is hearing you correctly before you finish.

It answers out loud

The reply is spoken sentence by sentence as it is generated, so audio starts before the model has finished writing the whole answer.

You can cut in

Start talking while it is speaking and it stops mid-sentence, drops the queued audio, abandons the turn, and listens to you instead.

Interrupting works the way it should

The thing that makes a voice assistant feel broken is having to wait politely for it to finish. Voice Mode is built around cutting in.

Talk over the answer

Speaking while it talks stops playback immediately, cancels the speech still being synthesized, and aborts the model's turn.

Interrupt while it thinks

Cutting in also works during the quiet stretch while the model reasons or runs a tool, not only once audio has started.

Your interruption is not lost

The words that triggered the interruption are captured from the pre-roll buffer, so what you said becomes the next message rather than being thrown away.

It resists false triggers

While speaking, the bar to interrupt is deliberately raised and the moment after each clip starts is ignored, so the assistant's own voice does not cut itself off.

Replies are written to be heard

In voice mode the model is steered toward short spoken sentences, and tables, bullets, headings, and code blocks are kept out of the audio.

Reasoning is turned off

Chain-of-thought is disabled automatically for spoken turns, because silent reasoning is dead air when you are waiting for a voice to answer.

Where your audio actually goes

Most voice assistants stream your microphone to a data centre. This one does not have a network call in the path at all. Here is every hop your voice takes.

Audio path, start to finish
Microphone Captured in the browser, with echo cancellation and noise suppression on. On device
Speech recognition Sent to a whisper.cpp process running on loopback on your own machine. On device
Speech synthesis Generated by a local worker process. No socket is involved at all. On device
Playback Raw audio handed straight back to the browser's audio output. On device

The audio never leaves the machine. The transcribed words follow your model choice. Once your speech becomes text, it is sent to whichever chat model the conversation uses, exactly like a message you typed. Pair Voice Mode with a local model and the entire conversation stays on your computer end to end. Point it at a hosted provider and the text goes there, as any typed message would. The recording itself is never uploaded in either case.

The only network traffic this feature generates is the one-time download of the engines and voices when you first set it up.

The engines and voices

Both halves are open source and downloaded on first use from the setup popover. You pick a voice quality tier; everything else is chosen for you.

PieceWhat runsNotes
Listening whisper.cpp, with Whisper Small as the default model Multilingual out of the box. A smaller English-only model and a larger, more accurate model are also available.
Speaking, Low Piper LibriTTS-R, English The fastest option and the smallest download. A good choice on modest hardware.
Speaking, Medium Kokoro 82M, the default Good quality across nine languages, balanced against speed.
Speaking, High Kokoro 82M English, full precision The best sounding option, English only.

Speech synthesis runs on the CPU by design, so it never competes with your language model for video memory. Speech recognition also defaults to the CPU, with an optional NVIDIA build on Windows for faster transcription. Both engines unload themselves after a few minutes idle.

What you need

Voice Mode is deliberately cheap to run. It asks for no video memory at all, so it sits alongside a large local model without taking anything from it.

Windows Supported

One-click setup for both engines. An optional NVIDIA build speeds up transcription if you have a CUDA card, though a plain CPU install works fine.

Linux Supported

One-click setup for both engines on x64. Transcription runs on the CPU.

macOS Not yet

The speech engine has no prebuilt macOS binary upstream, so Voice Mode cannot be set up on a Mac today. Every other local AI feature in LumaBrowser works normally there.

Graphics card Not required

Neither engine needs a GPU and neither reserves video memory. Speech synthesis is CPU-only by design so your language model keeps the whole card.

Worth knowing before you try it

Voice Mode is new, and the feel of it is still being tuned. Echo handling and the pause length that ends your turn are the two things most sensitive to your room and microphone. Headphones or a headset give the most reliable experience, since they remove the assistant's own voice from the microphone entirely.

It lives in the AI tab. The microphone button is in the chat composer there. The browser side panel and the shared web client do not have it.

Voice picking is by quality tier. You choose Low, Medium, or High, which selects the underlying voice model. Choosing an individual speaker or adjusting the speaking rate is not exposed yet.

Have a conversation instead of typing one

Voice Mode ships with LumaBrowser, free to download. Pair it with a local model and you get a spoken assistant that works on a plane, behind a firewall, or anywhere you would rather not send your voice to somebody else's server.

Download LumaBrowser - free Set up a local model
See what's new in 1.6 · back to lumabyte.com