· IDEAS · SIGNAL LOG
Concepts and thinking on voice, computing, and the tools we build. Some are RFCs, some are half-formed sketches, all are in flight.
Dictate into ChatGPT on a Mac with system-wide voice input. Talkie types at the cursor in the browser or desktop chat so prompts stay where you already write.
Dictate into Cursor on a Mac with system-wide voice dictation. Talkie pastes at the cursor so prompts, comments, and commit messages stay in the editor you already use.
Capture voice memos on iPhone and Apple Watch with Talkie, sync through your iCloud account, and continue on Mac for dictation, notes, workflows, and agents.
What local, on-device, and offline speech to text mean on a Mac — and how Talkie keeps core recognition on your devices when you want private, reusable dictation.
How Mac dictation and speech to text work today: Apple’s built-in tool, third-party apps, on-device vs cloud, and when Talkie is the better fit for private, reusable captures.
Use Talkie as a voice remote for agents on Mac: dictate prompts into Cursor or Claude Code, attach screen context, and keep captures as local data your CLI can query.
How we redesigned the Talkie homepage by running six parallel subagents in git worktrees, comparing directions side by side, and picking a winner.
Apple's FoundationModels framework on macOS 26 lets Talkie run AI processing entirely on-device — no API key, no network call, no cost per request.
We tested Apple's Foundation Models against 24 real Talkie use cases. Here is what works, what needs a prompt, and what runs without an external model fee.
Read a draft proposal for configuring Talkie from files. It defines rules, tools, workflows, and automations in a structured system stored in project folders.
Turn a batch of voice memos into linked Obsidian topic files, daily notes, and an index with four reusable prompts.
A 0.6B model matches the 1.7B on accuracy, runs 2.4x faster, and fits in 350MB. At some point the task stops needing more parameters.
VLM vs text-only, where to draw the line between code and model, and why picking the right model size is harder than it sounds.
Fine-tuning a 1.5B model to reconstruct shell commands from voice. 97% accuracy, 3GB of RAM, under a second on a phone.
The Talkie CLI turns your voice memos and dictations into structured data that any script, pipeline, or AI agent can work with.
The same voice memo, transcribed three different ways. From Apple Speech on iOS to Parakeet v3 with post-processing — each layer improves readability while preserving the speaker's intent.
GUI apps are growing command lines. Here's why we built one for a voice app, and what it lets you do with your data after you've spoken it.
An essay on capturing ideas away from a keyboard. Explore how local transcription and small language models can turn spoken thoughts into useful saved notes.