> ## Documentation Index
> Fetch the complete documentation index at: https://docs.anarlog.so/llms.txt
> Use this file to discover all available pages before exploring further.

# Transcription and AI

> Choose how Anarlog turns audio into text and text into useful notes.

Anarlog uses two model settings:

* **Transcription** turns meeting audio into a transcript.
* **Intelligence** creates summaries and powers chat.

Open **Settings → Transcription** or **Settings → Intelligence** to choose a provider and model.

[Models and providers](/models-and-providers) explains the current Anarlog Cloud routes, built-in on-device models, and how bring-your-own-provider requests work.

## Choose a setup

<CardGroup cols={2}>
  <Card title="Anarlog Cloud" icon="cloud">
    Sign in and choose Anarlog for the quickest setup. Hosted models require a paid Anarlog plan.
  </Card>

  <Card title="On-device transcription" icon="laptop">
    Download Soniqo on a supported Apple Silicon Mac, use Apple Speech when macOS 26 reports it available, or choose **On-device file** to pick a whisper.cpp `.bin`.
  </Card>

  <Card title="Your API key" icon="key">
    Configure a provider, enter its API key, then select it under Model being used. API keys stay on this computer and do not sync to other devices.
  </Card>

  <Card title="Local language model" icon="server">
    Connect LM Studio, Ollama, or Unsloth, or use Apple Intelligence on an eligible Mac.
  </Card>
</CardGroup>

Models labeled **Live** show text during the meeting. Models labeled **After recording** transcribe after you stop.

To keep transcription, summaries, and chat on your computer, follow [Use Anarlog offline](/offline). For every on-device transcription path, see [How can I use on-device models?](/help#use-on-device-models). To compare on-device, Cloud, and bring-your-own-key cost, see [How can I compare the costs of all the transcription options?](/help#compare-transcription-costs).

## Subscription providers

You can use an existing paid plan for Intelligence without a separate API key. Open **Settings → Intelligence → Configure Providers** and connect **Claude**, **ChatGPT**, **Grok**, **GitHub Copilot**, or **Kimi Code**. After the connection finishes, select that provider under **Model being used**.

## Apple Intelligence

On an eligible Mac running macOS 26 or later:

1. Turn on Apple Intelligence in **System Settings** and wait for its model to finish downloading.
2. In Anarlog, open **Settings → Intelligence → Configure Providers → Apple Intelligence**.
3. Select **System Language Model** under **Model being used**.

<Note>
  Apple Intelligence support is experimental and currently handles text only.
</Note>

## LM Studio

1. Install [LM Studio](https://lmstudio.ai/download) and download a model.
2. Start its local server on port `1234` and enable CORS.
3. In Anarlog, open **Settings → Intelligence → Configure Providers → LM Studio**.
4. Select the LM Studio model under **Model being used**.

## Ollama

1. Install [Ollama](https://ollama.com/download).

2. Start it and pull a model:

   ```bash theme={null}
   ollama serve
   ollama pull llama3.2
   ```

3. In Anarlog, open **Settings → Intelligence → Configure Providers → Ollama**.

4. Select the Ollama model under **Model being used**.

## Unsloth

1. Install [Unsloth Desktop](https://unsloth.ai/docs/desktop) and load a model.
2. Start its local server on port `8888` and copy the API key. It starts with `sk-unsloth-`.
3. In Anarlog, open **Settings → Intelligence → Configure Providers → Unsloth** and paste the API key.
4. Select the Unsloth model under **Model being used**.

Only models currently loaded in Unsloth appear in the list.

## What leaves your computer

Your app data remains local. Local transcription and local Intelligence providers process content on your computer. If you select Anarlog Cloud or another hosted provider, Anarlog sends the audio or text needed for that request to the selected provider.

See [Data, privacy, and retention](/data-and-privacy) for a feature-by-feature explanation.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.