The AI-powered note-taking app Granola is valued at 1.5 billion dollarsit has become a popular tool among tech industry founders and VCs. However, one developer believes there is a demand for a more private, local alternative that is available for a one-time fee and without a subscription. This led to the creation of a new Mac app called Talat.
Yorkshire, England based developer Nick Paynea self-proclaimed computer nerd, says the idea to create a local AI notebook came about mainly through a series of happy accidents.
“I think Granola is awesome; it’s a shining example of what you can do with an Electron app [a framework for building desktop applications] it was given enough love and care,” he told TechCrunch. “When I first tried it, I was impressed that it managed to record system audio on my Mac without recording video, which was the standard solution at the time. This led to a ton of research, uncovering a relatively new and poorly documented Apple API.”
To make it easier to work with this API (Core Audio Taps, which allows developers to tap into a Mac’s audio streams), Payne decided to create an open source audio library, AudioTee.
“During that time, I was slowly putting together a toolkit, but I never found anything that I felt could stand on its own as a product rather than just a trendy tech demo,” Payne said. “The state-of-the-art hosted transcription models — the same providers like Granola use — are incredible, and it’s really cool to see your speech unfold on the screen in near real-time. But it always bothered me that the exchange required not only my data, but also my audio data, my actual voice,” he added.
Then he stumbled upon a software toolkit called FluidAudioa Swift framework that enables full native, low-latency audio AI on Apple devices. It lets you run small, fast transcription models directly on the Mac’s Neural Engine — Apple’s exclusive hardware for AI processing.
That was the part that made Payne realize he could turn his research into a real product—one where your audio never leaves your Mac and your transcriptions aren’t stored on another company’s servers.
Talatwhere was built in parallel Payne’s longtime friend and former colleague, Mike Franklin, is the result of Payne’s interest in sound space. The result is a one-time 20MB purchase that doesn’t require creating an account or even sharing analytics data with developers. There are also no ongoing charges.
While some AI bookmarks may have more bells and whistles, Talat offers an enhanced feature set. It captures audio from your computer’s microphone when you’re in meeting apps like Zoom, Teams, Meet, and more, and transcribes it in real time. The app tries to assign speakers in real time, but you can reassign them as needed. You can also take notes, as well as edit, delete or split parts of a transcript. When the meeting is over, a local LLM creates a summary with key points, decisions and action items.
Notes, transcripts and summaries can also be searched on Talat.
Aside from the privacy angle, Payne said the goal is to give users more options.
“We focus on configuration and let users control where their data goes: choose your own LLM, automatic export to [notetaking app] Obsidian, webhooks that remove data when a meeting ends, MCP server,” which is a standardized way for AI tools to connect to external data sources, “to pull it on demand,” he explained.
Under the hood, the AI is a mix — “mostly stitched together and abstracted behind FluidAudio,” noted Payne, which he credits with doing much of the heavy lifting. For the summary part, the app defaults to an Al model called Qwen3-4B-4bit, which can work even on fairly modest hardware.
However, users can choose to switch it to any LLM cloud provider of their choice, or they can choose between two variants of Parakeet – speech recognition models developed by Nvidia – or point it to Ollama (a tool for running artificial intelligence models locally), giving them more control over the experience. Over time, Talat will add support for more built-in options and have integrations for other apps like Google Calendar and Notion.
At launch, users with M-series Macs (those with Apple processors starting with the M1) can download the app and try it for free with 10 hours of recordings before they decide to buy.
Talat it is available for $49 while in this pre-release version, which is still under active development.
When the app reaches version 1.0, the price will increase to $99.
Payne and Franklin are bootstrapping Talat and plan to keep the core product a one-time purchase going forward.
Updated after publication with Granola’s new valuation.
