Skip to main content
Browse a topic, then expand the question. If something is not working, go to Troubleshooting. For a question not covered here, email founders@anarlog.so or join Discord.

Transcription and cost

Anarlog has three cost models. Compare those first, then compare providers inside the one you choose.On-device and bring-your-own-key transcription stay on the Free plan. Cloud transcription is a Pro feature.For a bring-your-own-key provider:
  1. Open Settings → Transcription → Configure Providers.
  2. Open that provider’s Available models and API setup links.
  3. On the provider’s pricing page, compare live vs after-recording rates, language coverage, speaker labels, and any free tier.
  4. Select the model under Model being used and run a short test meeting.
Anarlog does not publish a live price table for third-party providers because those rates change. OpenRouter is one key that can reach several after-recording models if you want a single bill to compare.See How can I use on-device models?, Models and providers, and Transcription and AI.
On an Apple Silicon Mac, yes — transcribe after the meeting with Soniqo → Parakeet Batch. That built-in model adds speaker labels for 25 European languages and is the on-device option meant for long calls.Other local choices on the same Mac:
  • Soniqo → Parakeet Streaming shows text during the meeting. Use Batch when you care more about finishing a long recording than seeing live captions.
  • On-device file runs a downloaded whisper.cpp .bin model after recording. transcribe.cpp .gguf files are not supported yet.
  • Apple Speech is live-only and available when macOS 26 reports compatible system assets. It transcribes one supported language at a time.
Built-in on-device transcription is not available on Windows, Linux, or Intel Macs. On those systems, use a Deepgram-compatible local server, Anarlog Cloud, or a bring-your-own-key provider. After-recording hosted models handle hour-long audio. Some live models have short session limits — for example, Gemini 3.5 Transcribe Live preview sessions last up to 10 minutes.Quality and speed depend on the computer. Run a short test recording before a long call. See How can I use on-device models? and Use Anarlog offline.
Yes. Download the Windows x64 build and record from the desktop without a meeting bot. Windows support is in beta.Expect these differences from a Mac setup:
  • Built-in on-device transcription is not available. Choose Anarlog Cloud, a Deepgram-compatible local server, or another configured provider. See How can I use on-device models?.
  • Microphone detection, auto-stop, and meeting-chat capture are macOS and Linux only.
  • You can import Granola meeting history from an official export.
See Install the desktop app.

Recording and notes

No. Anarlog captures your microphone and computer audio from the desktop without adding a meeting bot. See Record meetings.
Yes. Anarlog can start calendar-backed meetings on schedule and prompt you when it detects an unscheduled call. Manage scheduled meeting controls under Settings → Meetings and microphone detection under Settings → Notifications. Microphone detection, auto-stop, and meeting-chat capture are available on macOS and Linux, not Windows. See Automatic capture.
Yes. Use Write to edit transcript text. Select text or a speaker label to assign the correct person, create a speaker, or apply the change to every matching segment. See Correct a transcript.
Yes. Right-click Transcript and choose Resume listening. The new recording stays in the same meeting note.
Yes. Upload one audio, SRT, or VTT file to an empty note, or use Settings → Imports for meeting-history exports from another assistant. See Import audio or a transcript and Import meeting history.

AI, offline use, and privacy

Anarlog can transcribe without sending audio to Anarlog Cloud. Open Settings → Transcription and pick the path that matches your computer.Soniqo, Apple Speech, and On-device file appear only on a supported Apple Silicon Mac. On Windows, Linux, or Intel Macs, use a local Deepgram-compatible server, Anarlog Cloud, or another configured provider.Summaries and chat are a separate setting. For those to stay local too, choose LM Studio, Ollama, Unsloth, or eligible Apple Intelligence under Settings → Intelligence.See Models and providers, Use Anarlog offline, and Is there a reliable local model that can handle hour-long calls?.
Yes, if you prepare local models before disconnecting. Soniqo, Apple Speech, and On-device file transcription require a supported Apple Silicon Mac; Apple Speech also needs macOS 26 to report compatible system assets. LM Studio, Ollama, Unsloth, and eligible Apple Intelligence can provide local Intelligence models. See Use Anarlog offline and How can I use on-device models?.
Settings → General → Language & Region lets you choose a main language and additional spoken languages from this list:Arabic, Belarusian, Bulgarian, Bangla, Bosnian, Catalan, Czech, Danish, German, Greek, English, Spanish, Estonian, Persian, Finnish, French, Hebrew, Hindi, Croatian, Hungarian, Indonesian, Italian, Japanese, Kannada, Korean, Lithuanian, Latvian, Macedonian, Marathi, Malay, Dutch, Norwegian, Polish, Portuguese, Romanian, Russian, Slovak, Slovenian, Serbian, Swedish, Tamil, Telugu, Thai, Filipino, Turkish, Ukrainian, Urdu, Vietnamese, and Chinese.The selected Transcription model must support those languages. Coverage today:Summaries and chat use the main language. See Use multiple languages.
There is no single hidden model. Your Transcription selection handles audio, and your Intelligence selection handles summaries, titles, and chat. Anarlog Cloud currently routes transcription by language and mode and routes text Intelligence tasks through the latest Claude Sonnet alias on OpenRouter. See Models and providers for the current routes and local options.
Anarlog stores app data locally by default. Hosted AI, calendars, sync, sharing, and the optional Cloud API receive the content needed for the feature you enable. See Data, privacy, and retention. Enterprise security reviews should start at the security page.
The answer depends on the provider you choose. Local providers keep the model request on your computer. For Anarlog Cloud or a bring-your-own-key provider, review that provider’s retention and training policy before sending sensitive content.
Yes. Choose the summary language and add every spoken language you expect. The selected Transcription model must support them. See Languages.

Sharing, sync, and automation

Anarlog shares the generated summary, not your private memo. Retained audio is optional and must be included separately. Sharing is a Pro feature. See Share meetings.
No. The key is shown only during setup and Anarlog cannot read or recover it. Save it in a password manager before closing the setup window. See Cloud sync.
No. Cloud Sync copies encrypted notes, not Transcription or Intelligence API keys. Enter each key again on the new computer, then select those models in Settings. See What Cloud Sync replicates.
Yes, with Anarlog Pro. Built-in starters can post a Slack recap, update a Notion page, create Linear issues, or export each meeting as Markdown. See Automate meeting follow-up.

Platforms and developer tools

Anarlog supports macOS 15 or later. Windows x64 and Linux x64 or ARM64 builds are available in beta. See Install the desktop app.
Not yet. Anarlog currently ships as a desktop app.
The CLI and local MCP server read the local database, so they work while the app is closed. They can also stage a memo or summary proposal; review the pending edit banner in the desktop meeting note before applying it. Webhooks only deliver while the app is open. For hosted access from anywhere, explicitly enable Cloud API & Connectors.