On-device AI

Speech processing always runs on your Mac: audio capture, transcription (Parakeet), speaker identification, echo cancellation, and voice detection. No setup, no plan requirement — audio never leaves the machine.

The AI features that work on transcript text — summaries, the live assistant, dictation cleanup, transform — are off until you choose a provider. Setup starts on Transcripts only, and the built-in cloud option is Google Gemini through our open-source proxy. This page is about running them on your own hardware instead. Two levels, in increasing order of setup:

You want	Use	Covers
No cloud AI for a meeting	On-device	Transcription and speakers on your Mac; off-device AI off
Every AI feature on your hardware	Custom endpoint → a local server	Dictation, Transform, summaries, live assistant

A local server: every feature

Any server that speaks the OpenAI chat-completions API works. Ollama is the shortest path:

1. Install Ollama and pull a model:

   ollama pull qwen3

2. In Settings → AI & Data, under Custom endpoint, fill in:

   • Base URL — http://localhost:11434/v1
   • Model — the name you pulled, e.g. qwen3.6:27b
   • API Key — leave blank
   • Reasoning — leave at Model default. It omits the field and lets the model use its own setting. None is the fastest option and stops a thinking model reasoning at length before every answer, but some models read it as permission to skip work — one returned an empty speaker list on all 78 calls of a test run, with no error. If you set it, check that speakers still get named.

   Click Verify. It checks the server is reachable, then sends a tiny request to confirm the model actually responds.

3. Under Feature routing, set the features you want to Custom endpoint. You can mix — summaries on your local model, dictation on Gemini.

LM Studio and llama.cpp work the same way; only the Base URL and model name change. The full reference — what routes where, plan limits, troubleshooting — is on the Custom AI Endpoint page.

What to expect

Own hardware means owning the quality tradeoff:

• Quality is the model you pick. MimicScribe’s prompts are tuned against Gemini. Dictation and transform are short, focused tasks that mid-size local models handle; meeting summarization is a long-context task — use the largest model your Mac runs comfortably.
• Meeting search and reference documents use the Post-meeting summary provider, and vocabulary hints use the Dictation provider. With Off there, they work without AI: search matches keywords, documents are used as written, and vocabulary is the words you added.
• Caps mostly don’t apply. Summaries on your own endpoint are always free. Pro and Cloud AI are uncapped; on the free tier the live assistant uses your free AI meetings (the first 30, then 5 a week; unlimited until January 1, 2027). See Free Tier.

Watch it work

Open Settings → Network Log and run a meeting or a dictation. Each AI request lists where it went — with a local server, that’s your own machine:

Network Activity documents what the log records and how to verify it from outside the app with nettop or Little Snitch.

On-device meetings: no cloud AI

Routing changes where the AI runs. On-device is different: it keeps one meeting away from every cloud AI. Transcription and speaker separation run on your Mac, no AI off your Mac sees it unless you switch that meeting back online, and a summary comes only from AI on your Mac. MCP tools and a webhook you turn on still reach it. Toggle it per meeting when you start one. Require on-device AI in Settings → AI & Data goes further: every meeting stays on-device, and no feature can use off-device AI until you turn it off. Details in Privacy & Data.