Skip to main content

​
Privacy and data

No. Steno processes all recordings using AI models that run locally on your Mac. No audio, transcript, or summary is transmitted to any external server. The only network requests Steno makes are the initial model download and a version check on launch.
All data is stored in ~/Library/Application Support/stenoai/:
  • recordings/ — raw .wav audio files
  • transcripts/ — verbatim transcript text
  • output/ — Markdown summaries and notes
Nothing is stored remotely.
No. The Steno app has no analytics, crash reporting, or usage tracking. (The Steno documentation site uses PostHog analytics separately from the app.)
Steno is designed for professionals handling confidential audio. Because processing is entirely local, it is suitable for use cases where sending audio to a cloud service is not acceptable — clinical consultations, legal calls, financial meetings. Review your organization’s specific policies before using any recording tool with regulated data. See Confidential use cases for more detail.

​
Installation and setup

Steno is signed but distributed outside the Mac App Store. On first launch, macOS Gatekeeper may block it. Go to System Settings → Privacy & Security and click Open Anyway next to Steno. This is a one-time step.
The default setup requires approximately 3GB: ~480MB for whisper-small and ~2GB for llama3.2:3b. Larger models take more space. Recordings accumulate over time in ~/Library/Application Support/stenoai/recordings/.
Steno updates automatically in the background. When an update is ready, you will see a notice in the app. The update installs on the next quit — you do not need to download a new DMG.
Delete Steno from your Applications folder. To also remove all recordings, transcripts, and model files, delete ~/Library/Application Support/stenoai/ and ~/.ollama/ (if you want to remove the Ollama models too).

​
Recording

Steno can capture system audio — the audio playing through your Mac’s speakers or headphones, which includes the other participants on a call. See Recording for setup instructions. System audio capture requires a one-time permission setup.
Yes. Steno records from your Mac’s microphone, which will pick up voices in the room. For best results, place your laptop centrally and use whisper-medium for cleaner transcription of in-person audio.
No. Steno captures audio from your Mac’s audio system without joining the call as a participant. Other attendees will not see a bot or receive a notification from Steno. Recording consent obligations are your responsibility.

​
Transcription and summaries

Switch to whisper-base in Settings → Models → Transcription for faster processing at slightly lower accuracy. On Apple Silicon, whisper-small processes a 30-minute meeting in roughly 2-4 minutes.
Switch to a larger summarization model. In Settings → Models → Summarization, try qwen3.5:9b or deepseek-r1:14b. Larger models produce more detailed and accurate notes. You can re-summarize any existing recording from its detail view.
Yes. Whisper supports 99 languages. Steno auto-detects the language from the audio — no manual configuration is needed. English, Spanish, French, German, Japanese, and Chinese perform particularly well.

​
Models

Transcription: Whisper (base, small, or medium). Summarization: any model supported by Ollama, with llama3.2:3b as the default. See Transcription models and Summarization models for the full comparison.
Yes. Steno optionally supports OpenAI, Anthropic, or a custom API endpoint as an alternative to the local model. Configure this in Settings → Models → Summarization → Cloud model. Note that this sends your transcript (not audio) to the selected provider’s API.