Skip to main content
To keep audio and post-processing on your device, set a local transcription model and a local AI model. This guide shows how to keep both transcription and AI post-processing on your device so your data stays private and works without the internet.

​
Overview

Utter can run fully local in two stages:
  1. Local transcription: Choose an on-device speech model (Parakeet) for voice-to-text.
  2. Local AI processing: Point Utter to a local OpenAI-compatible server (LM Studio or Ollama) for post-processing.

​
Stage 1: Use Local Transcription Models

To make transcription fully local, switch the default transcription model to a Parakeet model.
1

Open Advanced Settings

In Utter, go to Settings > Advanced Settings.
2

Change the Default Transcription Model

At the top of Default Models, select a Parakeet model for Transcription. Built-in models are marked with a MacBook icon in the model list.
Select a Parakeet local voice model in Utter advanced settings
3

Let the Model Download

Selecting a Parakeet model automatically downloads it. Once downloaded, all transcription runs locally on your device.
What to expect: New recordings use the Parakeet model and continue working without internet for transcription.
When a Parakeet model is selected, transcription stays on-device, requires no internet, and remains private.

​
Stage 2: Use Local AI Processing (LM Studio or Ollama)

Utter can also run AI post-processing locally by connecting to a local OpenAI-compatible server. Two popular options are Ollama and LM Studio. The steps below walk through LM Studio.
1

Enable Power User Mode and Open the Developer Tab

Open LM Studio, enable Power User Mode, then open the Developer tab.
LM Studio power user mode and developer tab
2

Load a Model and Start the Server

Make sure a model is loaded, enable the server, then copy the Model ID and Base URL from the Developer tab.
LM Studio server enabled with model ID and base URL
3

Open Utter Custom Models

In Utter, go to Settings > Advanced Settings > Custom Models, then choose Custom OpenAI Compatible as the provider.
Utter custom model provider set to OpenAI compatible
4

Add the Local Model

Click Add Custom Model. Paste the Model ID and Base URL, then click Test to verify the connection and Save.
Utter add custom model form with model ID and base URL
5

Set the Local Model as Default

In Default Models for AI models, select the newly created model (it has a key icon). This makes it the default for all AI post-processing.
Set the LM Studio model as the default AI model in Utter
What to expect: AI output uses your local model and no external AI provider is required. If that did not work: Click Test in the custom model form again, verify the local server URL and model ID, then save and reselect the model.
Once the key-icon model is selected, Utter uses your local model for AI post-processing. No internet is required and everything stays private on your device.

​
Option B: Ollama (Quick Notes)

If you already use Ollama, you can also configure it as an OpenAI-compatible provider and follow the same Custom Models steps above. The key requirement is a local server URL and a model ID exposed by your Ollama setup.