Notes take too long on my machine
Transcription is fast on any Apple-silicon Mac. Notes are the slow part, because by default they come from a language model running entirely on your Mac through the built-in engine, and that model needs memory. On a Mac with 8 GB the engine picks Qwen2.5 1.5B; from 16 GB up it picks Qwen3 4B. Either can be chosen under Settings → AI notes → Model.
What to expect
Measured on an 8 GB M-series Mac:
- With Qwen2.5 1.5B, the model the engine picks on 8 GB: about 35 seconds for a 5-minute clip, so roughly five minutes for a 40-minute meeting.
- With the larger Qwen3 4B model: a 39-minute meeting took about 12 minutes, and an 18-minute meeting about 4 minutes.
- The machine stays responsive throughout.
On a 16 GB Mac the engine picks Qwen3 4B. While notes are being written, the meeting shows how long the writing has taken so far.
If basic notes show first
When the notes for a call take longer than usual, Recordist shows basic notes that quote the transcript first, so you have something to read at once. The full notes keep being written while Recordist stays open, and when they are ready they replace the basic notes by themselves, with a short notice. Nothing is needed from you; if you quit before they finish, choose Regenerate in that meeting’s AI notes panel.
Three ways to speed it up
1. Use your own cloud key. Under Settings → AI notes → Notes are written by, choose Anthropic or an OpenAI-compatible provider and paste your key. The transcript text, the meeting’s title, attendee names and date, and your template are sent directly to that provider, and the Privacy Ledger records every request. The audio is never sent to the provider. This is the recommended setup on 8 GB machines.
2. Stay with the smaller local model. On 8 GB machines the engine already picks the 1.5B model, which is noticeably faster and still produces usable summaries and action items. If you switched to Qwen3 4B for quality, you can switch back under Settings → AI notes → Model.
3. Turn off automatic notes. With Write notes automatically when a recording stops off in Settings → AI notes, nothing runs until you click Generate in a meeting’s AI notes panel, so short calls that do not need notes never cost you a wait. This also helps you stay within the 3 notes a month on the Free plan after the trial.
Why two defaults?
Because notes quality matters more than speed for most people, and Qwen3 4B is the smallest model that reliably gets decisions and owners right, so it is the default from 16 GB up. On 8 GB it took about 12 minutes for a 39-minute meeting, which is why the engine starts with the 1.5B model there. You can change it under Settings → AI notes → Model.