Skip to main content

Documentation Index

Fetch the complete documentation index at: https://isaree-cd4b6397.mintlify.app/llms.txt

Use this file to discover all available pages before exploring further.

Scribe runs inside a Patient Chat. You record audio — a visit, or your own dictation — a Scribe Agent transcribes it and extracts the fields its template defines, and you send the structured draft into the chat as Markdown.
Isaree is a research version. Record synthetic visits only — no real patient audio.

​
Prerequisites

  • At least one Scribe Agent downloaded from the Isa Hub.
  • A patient to attach the Scribe session to — Scribe doesn’t run in Workspace.

​
Start a Scribe session

Open a Patient Chat and start a Scribe session from the round purple Scribe button on the right of the composer. The button is only visible when the composer is empty — start typing and it tucks itself away.

​
Choose a template

The Select Template sheet groups templates by the Scribe Agent that ships them. Pick the template that matches the note shape you want, and recording starts straight away. There’s no separate start step.

​
Record the visit

Recording shows a live waveform, a running timer, and three controls — discard, pause, stop. Stop ends the recording and starts processing: transcription, then diarization if the Scribe Agent ships a Diarization Model, then extraction against the template’s fields.

​
Review the structured draft

When processing finishes, Isa shows the structured draft. The header carries the template name and a timestamp (SOAP - 25 May 2026, 14:16). The Original Transcript at the top expands to show the raw transcription — labeled by speaker if the Scribe Agent uses diarization, otherwise as one continuous block. Useful when you want to double-check what the Scribe Agent heard against what it extracted. Below the transcript, each field defined by the template renders as an editable section with a name, a short description, and a character counter. Edit any section directly before you send.
The quality of the extracted fields is bound by whichever model runs the Extraction step. If extractions look thin or repetitive, pick a stronger Primary Agent model (Extraction → On-Device uses the Primary Agent’s loaded on-device model) or route Extraction to OpenAI in Settings. See Choose a model.

​
Send the draft into the Patient Chat

Save & Confirm drops the draft into the Patient Chat composer as Markdown, with each template field rendered as a section. Review the Markdown, edit as needed, and send. Cancel discards everything — the recording, the transcript, and the extraction — and returns you to the chat.

​
Route transcription and extraction

Two settings control where the work runs, independently of each other:
  • Transcription — On-Device or ElevenLabs (cloud, your API key). On-Device uses the ASR Model the Scribe Agent ships, plus its Diarization Model if it has one. ElevenLabs replaces both with its own speech-to-text and (when needed) diarization.
  • Extraction — On-Device (reuses the Primary Agent’s loaded on-device model) or OpenAI (cloud, your API key).
Set both from Settings. A Scribe session is fully on-device only when both are On-Device and the active Primary Agent is on-device.

​
Understand what leaves your device

  • The recording is processed by whichever provider you’ve routed Transcription to. On-Device keeps the audio on the iPhone or iPad; ElevenLabs sends it off-device.
  • The transcript is processed by whichever provider you’ve routed Extraction to. On-Device keeps the transcript on the device; OpenAI sends it off-device.
  • The structured draft lands in the Patient Chat once you send it. Where the chat goes from there depends on the Primary Agent’s own routing — see Data and privacy.

​
Next

Patient Chat

Where Scribe runs and where the draft lands.

Settings

Route Transcription and Extraction.

Build a Scribe Agent

Build your own template and ASR model on the Community Hub.