Available now · requires macOS 26 or later AI on your Mac · not in the cloud

Find anything you’ve heard

Audient transcribes the meetings, voice memos, and talks already on your Mac, then makes the archive searchable in plain English. On-device, no upload.

Download on the Mac App Store See how it works

Free to download · One-time unlock from £14.99

Audient
what did the witness say about the second invoice
14 passages across 9 recordings
23:14Tue, 14:02

Interview, Marta Lindqvist

“The second invoice was the one that didn’t match the contract. I flagged it to my line manager in March and nothing happened. Then in May the auditors arrived.”

0.94
04:38Mon, 09:11

Field note

“Reminder for myself, cross-check the second invoice figure against the filing the company made to Companies House. Marta said £48,000, the filing says £52,400.”

0.88
41:02Fri, 16:30

Source call, former finance lead

“There were two invoices. The first one was clean. The second invoice went out a fortnight later and that’s the one nobody on the team had signed off.”

0.81
12:5519 Apr

Background briefing, counsel

“On the record, the second invoice is the document the regulator will want to see first. Don’t lead with the email chain, lead with the invoice.”

0.74
Cite “The second invoice was the one that didn’t match the contract. I flagged it in March and nothing happened.” interview-lindqvist-2026-04-21.m4a · 23:14
What it does

Four things, done locally.

Audient is small on purpose. It imports the audio and video files you choose, turns them into searchable text on your Mac, and lets you cite the exact moment something was said. No accounts, no servers, no syncing.

Local-first semantic search

Ask in plain English and Audient returns the exact passages from across every meeting, call, and voice note in your library. Embeddings are computed and stored on your Mac.

Index·SQLite + on-device vectors

On-device transcription

A speech model runs locally and produces word-level timestamps for everything you capture. Audio never leaves the device. Works offline on a plane, in a basement, anywhere.

Model·optimised for on-device inference

Citations you can paste

Every result links back to the exact second in the source recording. Copy a quote and Audient pastes the verbatim line, the file, and the timestamp, ready to drop into a doc or a Slack message.

Format·plain text

Bring your own LLM

Audient exposes a local MCP server on your Mac, and only software on the same Mac can reach it. Claude Code is set up with one command. Other assistants that support MCP can connect too, as long as the connection comes from your Mac and not from their provider’s servers. If your assistant uses a hosted model, it sends the passages it reads to its provider. Audient itself stays put either way. This connection is the part Pro adds, and your trial includes it.

Protocol·MCP (Model Context Protocol)
How it works

Set it up once, then drive it explicitly.

You decide what enters your library, what gets transcribed, and what gets indexed. Audient does none of that on its own. It does fetch a small settings file from our website when it opens and once an hour while its window is open, and that request sends nothing from your library.

  1. 01

    Bring in a recording

    Open a file with the picker, or drop one onto the window. Audient never goes looking for files on its own.

    Open with the file picker Drag onto the window
  2. 02

    Audient transcribes locally

    Once you add a recording, the on-device model transcribes it with word-level timestamps. A progress bar in the Audient window shows how far it has got.

    No upload, no API key Cancel at any time
  3. 03

    Search and cite

    Hit ⌘F, ask in plain English. Results come back with a direct quote, the source file, and a clickable timestamp that opens the audio at exactly that moment.

    Semantic, not just keyword Filter by source or date Copy-as-citation in one click
  4. 04

    Plug in an LLM (optional, with Pro)

    Audient exposes its archive through a local MCP server that only your Mac can reach. Claude Code has a ready-made command. Other assistants that support MCP work too, as long as they connect from your Mac and not from their provider’s servers. If your assistant runs its model locally, your library stays on your Mac. If it uses a hosted model, the passages it reads go to that model’s provider. You can also call it over plain HTTP from your own script.

    Claude Code in one command Local or hosted LLM, your call Or plain HTTP from a script
Pricing

Free to try. Paid once, then it’s yours.

Audient is free to download, and a 14-day trial gives you everything. After that, Standard is a one-off £14.99 covering import, transcription and search, and Pro is a one-off £39, adding the AI assistant connection. Standard owners can upgrade to Pro for £23.99. Playing a recording and exporting its transcript stay free for everyone, with a purchase or without one. No subscription, no metering.

Audient for Mac
Free to try then one payment of £14.99 or £39, yours forever

Free to download on the Mac App Store. Localised pricing.

No subscription, no account, no cloud.

Get Audient

Free to download from the Mac App Store. The 14-day trial runs first, then one purchase, £14.99 for Standard or £39 for Pro, unlocks it for good.

Download on the Mac App Store