laurence/openscribe
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
openscribe/server/README.md
Laurence 031074c9a9
Some checks failed
ci / firmware (push) Failing after 2s
Details
ci / server (push) Failing after 45s
Details
scaffold: OpenScribe open-source self-hosted AI voice recorder 
Bootstrap of the project (M0). Sets up the monorepo, design docs, hardware BOM,
the open API contract, component skeletons, licensing and CI, following the
Default Workflow SOP.

What changed:
- CLAUDE.md + docs/: copied the Default Workflow so sessions load the SOP.
- state/: PROJECT, ARCHITECTURE, DECISIONS, TODO, NOTES filled in for OpenScribe.
  ARCHITECTURE captures the four-part design (firmware, server, app, case) and the
  three sync paths; DECISIONS records the hardware, AI-stack, storage, app and
  licensing choices; TODO lays out milestones M1-M9.
- hardware/BOM.md: two build options (compact XIAO ESP32-S3 Sense; dev ESP32-S3 +
  I2S mic + SD), wiring/pinout, indicative cost.
- api/openapi.yaml: the completely open API (device + server surfaces), including
  recording list/download/delete and exports (wav/ogg/txt/srt/vtt/md/json).
- firmware/: PlatformIO ESP32-S3 project, two board profiles, pin map, boot scaffold
  with module seams for M1-M4.
- server/: FastAPI skeleton mirroring the OpenAPI, config for self-hosted MinIO,
  faster-whisper and Ollama; stub routes browsable at /docs.
- app/, case/: Flutter app plan; parametric OpenSCAD enclosure.
- Licensing: GPL-3.0 (code), CERN-OHL-S-2.0 (hardware), CC-BY-SA-4.0 (case/docs),
  REUSE-style LICENSES/ with SPDX headers; LICENSING.md explains the split.
- CI: Forgejo Actions workflow builds firmware (both profiles) and lints/imports server.

Why:
- Everything self-hosted and openly licensed per the user's requirements: an open
  API, three sync paths (BLE control, WiFi transfer, independent WiFi upload on
  charge to generic cloud storage), and a full self-hosted transcription+summary stack.

Notes:
- No custom PCB in v1; off-the-shelf modules. Physical verification waits on parts.
- Component code is stubs at M0; features land milestone by milestone, each as its
  own branch/PR per the workflow.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-03 10:21:37 +01:00

1.5 KiB
Raw Blame History

OpenScribe server

Self-hosted FastAPI server: ingests recordings, transcribes them (faster-whisper), summarises them (Ollama), and serves the open API with exports. Everything runs on hardware you own.

Status: M0 scaffold. The API shape is live and browsable at /docs with in-memory stubs. Transcription lands in M5, summaries in M6, real storage/DB alongside.

Run (dev)

cd server
python -m venv .venv
. .venv/Scripts/activate     # Windows;  or:  . .venv/bin/activate
pip install -r requirements.txt
cp .env.example .env         # edit as needed
uvicorn app.main:app --reload

Self-hosted dependencies

For the AI features (M5/M6) you run, on your own kit:

  • MinIO (or WebDAV / NAS) for object storage - OPENSCRIBE_STORAGE_BACKEND=s3.
  • Ollama for summaries - ollama serve and ollama pull llama3.1.
  • faster-whisper downloads its model on first use; CPU works, CUDA is faster.

None of these are required for plain recording and transfer; they add transcription and summaries.

Layout

app/main.py     FastAPI app + routes (mirrors ../api/openapi.yaml)
app/config.py   Settings from env / .env
app/models.py   Pydantic models (kept in sync with the OpenAPI schemas)
requirements.txt
.env.example

API

The contract is ../api/openapi.yaml. The device implements the LAN "device" paths; this server implements ingest, transcript, summary and export.