Features

Features below are grouped by what you reach for them for, not by where they live in the menu. Pro features are marked. Mixed features call out which parts are Free and which parts require Pro.

Capture

Recording

One-shortcut start: Cmd+Shift+R (macOS) or Ctrl+Shift+R (Windows / Linux). Captures microphone and (optionally) system audio simultaneously. Pause / resume with Space; stop with the same shortcut or Escape.

The recording surface shows a live audio meter (so you can confirm you're being heard), a running timer, and the live transcript scrolling in as you speak.

Transcription

Whisper.cpp running locally with GPU acceleration where available (Metal on Apple Silicon macOS, CUDA on NVIDIA, Vulkan on AMD/Intel). Many languages with auto-detect. Multiple model sizes from tiny (~39 MB) up to large-v3 (~2.9 GB) — pick the trade-off between speed and accuracy that suits your hardware.

RMS voice activity detection strips silence before transcription, cutting processing time by 10-60% on real-world recordings. Optional Silero neural VAD is available when the model is downloaded and the setting is enabled. Long recordings stream segment by segment so you can read what's already done while the rest catches up.

Import

Already have a recording? Import MP3, M4A / AAC, FLAC, OGG, or WAV files. Symphonia handles the decoding; the file joins the same transcription pipeline as a live recording, so the output and the downstream features are identical.

Summarise

Local summarisation (Built-in AI, on-device)

Built-in AI runs Mistral and EuroLLM models on-device via llama.cpp on macOS, Windows, and Linux. It is the default for new installs; no internet is required after download, and no data leaves your machine. Ollama and optional Pro cloud are additional provider choices. Choose your tier based on hardware:

• Ministral 3B Instruct (~2 GB) — the recommended starting point. Runs comfortably on 8 GB RAM.
• Ministral 8B Instruct (~4.6 GB) — sharper reasoning for dense, multi-topic recordings. 16 GB RAM recommended.
• EuroLLM 9B (~5.3 GB) — best for European language mixing and code-switching. 16 GB RAM recommended.
• Mistral Nemo 12B (~7.1 GB) — highest local quality for long, complex lectures. 24 GB RAM recommended.

Cloud summarisation (Pro, BYOK)

Pro unlocks cloud providers with your own key: Mistral, OpenAI, and Anthropic. BYOK does not unlock cloud access on Free. Ollama is a separate Free local provider. Gemini is legacy-only for existing saved keys. Managed keyless cloud is planned for v2.1, not live.

Reading-style preferences

Three densities, configurable globally and per session:

• Just the highlights — skim-friendly bullets, ~30-second read.
• Good balance — structured notes with key terms, ~2-minute read.
• Full picture — long-form recap with context, ~5-minute read.

Behind a "+2 More preferences" expander you can also tune structure (bullets / mixed / paragraphs) and visual emphasis. Defaults are sensible — most users don't need to open it.

Recall (study-time features)

Study Sage chat and modes

Conversational AI grounded in the transcript and summary of your recordings. Open with Cmd+Shift+K / Ctrl+Shift+K. Four modes:

• Chat (Free): open conversation about the material.
• Quiz (Pro): generate questions to test recall.
• Explain (Pro): re-explain a concept in plainer language.
• Challenge (Pro): push back on what you think you know.

Recall Engine (Pro)

Auto-generated flashcards from meeting summaries. Cards live in the current review session only. They are not stored between sessions and there is no SM-2 scheduler in this version.

Exam Radar (Pro)

Cross-meeting concept analysis. Looks across an entire semester of recordings and surfaces the topics that recur most often, the concepts most likely to appear on an exam, and the gaps in your existing coverage. Useful in the last two weeks of a module.

Action items and decisions (Pro)

On-demand extraction of Tasks, Decisions, and Open Questions from a meeting. Useful for meeting recordings; less useful for solo lectures.

Search and analytics

Search

Meeting search in the sidebar and Meetings page is title-only substring matching. Content search happens through Study Sage, which uses SQLite FTS5 with BM25 ranking across transcripts and summaries. Date, language, speaker, and tag filters are not in the current user-facing search UI.

Lecture analytics dashboard (Pro)

Topic coverage over time, duration trends, keyword frequency, speaker identification, and an at-a-glance health view of your recording practice across a term.

Export

PDF export (Pro)

Render any meeting summary as a formatted PDF with the meeting title, date, NeuroBridgeEDU logo, page footer, and summary body. The current PDF export does not include the raw transcript, separate action items, timestamps, or diagrams.

Plain-text and Markdown

Copy any summary or transcript as plain text or Markdown — free, no subscription. The format you pick matches what most note-taking apps expect.

Accessibility features (always on)

• Full keyboard navigation with a Command Palette (Cmd+K / Ctrl+K).
• Screen reader semantics — native landmarks, no DIY ARIA widgets.
• Respects prefers-reduced-motion system-wide.
• Low-stim mode desaturates colour and disables ambient motion entirely; focus mode hides chrome so the recording surface is the only thing on-screen.
• 32 UI languages.
• Lexend as the body face — designed for reading proficiency, particularly helpful for dyslexic users.

For deeper detail on any of these, see the corresponding markdown file in the v2 app's documentation/03-features/ folder.