FerriScribe listens to your doctor-patient conversations and generates structured SOAP notes using a local AI model of your choice that runs entirely on your computer. Document OCR, multi-device sync over Tailscale. No cloud APIs. No data transmission. No subscriptions. HIPAA-compliant by design — because nothing ever leaves your device.
System prompt systematically optimized and benchmarked across 21 real clinical cases. Achieves 90%+ schema compliance with zero fabricated patient data — every field defaults to "Not discussed" unless explicitly stated in the transcript.
All processing on-device. SQLCipher-encrypted database (AES-256). Audio recordings encrypted at rest with AES-256-GCM. No cloud APIs, no data transmission. HIPAA-compliant by architecture.
Records the consultation, transcribes speech to text, and generates a structured SOAP note — ready for your review before the next patient sits down.
Context templates for visit types, custom vocabulary find/replace rules, 6 letter audiences (Patient, Insurance, Tax Authority, Specialist, Employer, Legal) plus custom audiences. Generate referrals, clinical letters, synopses, and peer discussions with per-document custom prompts.
Audit every line of code. Fork it, contribute, or customize it for your clinic. No black boxes, no vendor lock-in, no future price hikes.
macOS, Linux, and Windows. Runs on any capable machine with 16GB+ RAM — from a MacBook Air to a clinic workstation.
No per-seat licenses. No API fees. No cloud subscriptions. Download it, run it, own it. One less line item on your practice budget.
Bidirectional content sync over LAN or Tailscale. Transcripts, SOAP notes, letters, referrals, and audio stay consistent across machines. Background sync every 5 minutes with real-time SSE updates.
Proven on Apple Silicon Mac Studio with 192GB unified memory. Runs quantized models (Qwen 3.6 35B A3B) via LM Studio. Remote STT option lets you offload Whisper to an office server — no GPU server, no special equipment needed.
7,122 bundled BC MSP ICD-9 diagnostic codes with intelligent candidate selection. Keyword-overlap inverted index enriched with medical synonyms, plus specificity adjustment favoring precise codes. Off-list codes flagged with amber chips.
Drop supporting documents (PDF, images, Word, Excel, TIFF) to extract text via a local vision model. OCR'd content automatically threads into SOAP notes, referrals, and letters alongside patient context.
Generated documents display in a collapsible preview directly in the Generate tab — no need to switch tabs. Review SOAP notes, referrals, and letters in context.
Offload Whisper transcription to any OpenAI-compatible Whisper server on your LAN or Tailscale. Heavy model runs on your office server; laptops stay light.
Export SOAP notes as PDF, DOCX, or FHIR R4 — the healthcare interoperability standard. Share structured clinical documents with any EHR system. Audio recordings exportable as standard WAV files.
Space to record/stop, Cmd/Ctrl+Enter to generate SOAP notes. RSVP speed reader for rapid document review at configurable WPM with per-section filters. Drag-and-drop condition chip reordering.
SQLCipher AES-256 encrypted database with OS keychain integration. AES-256-GCM encrypted audio at rest. PBKDF2-HMAC-SHA256 key derivation. PHI-redacted log export for safe support. Soft-delete with undo toast.
Persistent condition tracking with drag-and-drop reorder. Real-time sync across paired devices via SSE. Tombstone-based conflict resolution ensures consistency across your practice.
Hit record before the consultation. FerriScribe captures audio and transcribes it locally with Whisper speech-to-text.
Enter medications, allergies, conditions. Drop supporting documents (PDFs, images, Word, Excel) for OCR extraction — content threads into all generation types.
The local AI model produces a structured SOAP note with ICD-9 codes, differential diagnoses, and plans — guided by context templates and your custom vocabulary.
Preview inline, edit, or review with the RSVP speed reader. Export as PDF, DOCX, or FHIR. Copy into your EMR — done before your next patient.
FerriScribe runs entirely on your local machine — no cloud APIs, no data transmission, no third-party servers. Patient conversations never leave your device. This isn't a privacy policy you have to trust; it's an architecture you can verify. Every line of code is open source and auditable.
FerriScribe isn't a prototype — it's running daily in a real family practice, generating SOAP notes from actual patient encounters. Here's the reference deployment:
Native Apple Silicon support with MLX optimization. Runs great on MacBook Air, MacBook Pro, and Mac Studio with M-series chips.
Full NVIDIA CUDA and AMD ROCm support. Run it on your workstation, a home server, or a dedicated clinic machine.
DirectML and CUDA support. Works on any capable Windows laptop or desktop with sufficient RAM for local inference.
The only requirement: a computer with enough RAM to run local models (16GB+ recommended).