Open-source AI medical scribe for encounter recording and clinical note generation.
Record patient encounters and generate structured clinical notes automatically.
OpenScribe is an open-source medical scribe designed to record patient visits, transcribe audio, and draft structured clinical notes. It suits clinicians looking for an alternative to proprietary medical scribing software.
The tool operates in a mixed mode combining local Whisper transcription with Anthropic Claude for note generation. Alternatively, you can use a fully local desktop path forked from StenoAI.
It suits tech-forward clinicians who want control over their transcription and documentation workflow. It does not suit practices needing out-of-the-box HIPAA compliance, as the project is still working toward it.
Record patient interactions directly within the application.
Utilizes local Whisper for audio-to-text processing in mixed mode.
Generates structured draft clinical notes using Anthropic Claude.
Download pre-built installers for desktop use without a full dev setup.
Free under the MIT licence. The only operating costs depend on whether you use paid cloud LLM APIs like Anthropic Claude or run fully local models.
885 open remote AI-training roles, updated November 17, 2026; most pay $20–$175 an hour. Zekai lists them free; the application goes to the employer’s platform.
These reviewed AI tools do the same job instantly — from our scored directory.
Not yet. The team is actively working toward HIPAA compliance, so you should evaluate its current state before using it with real patient data.
The default web deployment uses local Whisper for transcription and Anthropic Claude for note generation, with a fully local desktop path also available.
See Zekai first in Google