obsidian-plugin/mssoftjp_obsidian-voice-input
1
0
Fork 0
mirror of https://github.com/mssoftjp/obsidian-voice-input.git synced 2026-07-22 16:40:28 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
mssoftjp_obsidian-voice-input/docs/PROCESSING_FLOW.md
mssoftjp e4904d2e4c build(deploy): unify to npm run deploy; remove iCloud-specific script 
package.json: set deploy -> deploy-local alias and drop deploy-icloud.\nREADME: update deploy instructions to use Obsidian config vault detection + troubleshooting.\ndocs: add docs/PROCESSING_FLOW.md.\nNote: scripts/ and memo/ are gitignored; corresponding local updates are not tracked.
2025-10-29 03:07:36 +09:00

545 B
Raw Blame History

Processing Flow (High Level)

This document outlines the high‑level processing pipeline for Voice Input.

  • Capture audio from microphone (WebAudio)
  • Voice Activity Detection (VAD via fvad-wasm)
  • Buffering and segmenting frames
  • Encode and send via Obsidian requestUrl
  • OpenAI Audio Transcriptions (GPT‑4o Transcribe / GPT‑4o mini Transcribe)
  • Optional post‑processing (dictionary‑based clean up)
  • Render transcript in the Voice Input view; quick actions (copy/insert/append)

Details will be expanded in future revisions.