Talat’s AI meeting notes live on your device, not the cloud

Granola, the AI-powered notetaking app valued at $250 million, has gained traction among tech founders and venture capitalists. But one developer sees demand for a more private, fully local alternative available for a one-time fee with no subscription. That vision led to a new Mac app called Talat.

Nick Payne, a self-described computer nerd based in Yorkshire, England, says the idea for a local AI notetaker emerged largely from a series of fortunate accidents.

“I think Granola is amazing; it’s a shining example of what you can achieve with an Electron app when you give it enough love and care,” he told TechCrunch. “When I first tried it, I was fascinated by how it managed to record system audio on my Mac without also recording video, which was the standard workaround at the time. That set off a lot of research, leading me to discover a relatively new and poorly documented Apple API.”

To make working with that API (Core Audio Taps, which lets developers tap into a Mac’s audio streams) easier, Payne decided to create an open source audio library called AudioTee.

“During that time, I was slowly putting together a toolkit, but I never found anything that felt like it could stand on its own as a product rather than just a cool tech demo,” Payne said. “The state-of-the-art hosted transcription models — the same providers apps like Granola use — are incredible, and it’s viscerally cool to see your speech unfurled onscreen in near real time. But it always nagged me that the trade-off meant providing not just my data, but my audio data; my actual voice,” he added.

He then stumbled upon a software toolkit called FluidAudio, a Swift framework that enables fully local, low-latency audio AI on Apple devices. It lets small, fast transcription models run directly on the Mac’s Neural Engine — Apple’s dedicated hardware for AI processing.

That was the piece that made Payne realize he could turn his research into an actual product — one where your audio never leaves your Mac and your transcripts aren’t stored on another company’s servers.

Talat, built alongside Payne’s longtime friend and former colleague Mike Franklin, is the result of Payne’s interest in the audio space. The result is a 20MB download with a one-time purchase price, no account required, and no analytics data shared back with developers. There are no ongoing fees either.

While some AI notetakers may offer more bells and whistles, Talat provides a streamlined set of features. It captures audio from your computer’s microphone during meetings in apps like Zoom, Teams, Meet, and others, transcribing it in real time. The app attempts to assign speakers in real time, but you can reassign them as needed. You can also take notes, and edit, delete, or split transcript segments. When the meeting ends, a local LLM generates a summary with key points, decisions, and action items.

The notes, transcripts, and summaries are all searchable within Talat.

In addition to the privacy angle, Payne said the goal is to give users more flexibility.

“We’re leaning into configurability and letting users control where their data goes: pick your own LLM, auto-export to [notetaking app] Obsidian, webhooks that push data out when a meeting finishes, an MCP server,” which is a standardized way for AI tools to connect to outside data sources, “to pull it on demand,” he explained.

Under the hood, the AI is a mixture — “mostly stitched together and abstracted behind FluidAudio,” Payne noted, crediting FluidAudio with doing a lot of the heavy lifting. For the summarization piece, the app defaults to an AI model called Qwen3-4B-4bit, which can run on fairly modest hardware.

However, users can opt to switch that out to any cloud LLM provider of their choice, or choose between two Parakeet variants — speech-recognition models developed by Nvidia — or point it at Ollama (a tool for running AI models locally), giving them more control over the experience. In time, Talat will add support for more built-in choices and integrate with other apps, like Google Calendar and Notion.

At launch, users with M-series Mac computers (those running Apple’s own processors, starting with the M1) can download the app and try it out for free with 10 hours of recordings before deciding to purchase.

Talat is available for $49 while in this pre-release version, which is still under active development.

When the app hits a 1.0 release, 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.