Pick a recorded session to open its speaking-activity analysis and cut it into scenes.
Bring in per-person tracks from Riverside, Zoom, or anywhere — pick the folder, we do the rest.
Loading…
This session hasn't been processed. Do it right here in the browser — open the session folder and Process episode builds the analysis, transcript, auto-edit and show notes for you. No command line needed.
Power users can run the pipeline on the host machine from the project root (replace the path with your session folder):
node tools/analyze.mjs "<session-folder>" --push node tools/transcribe.mjs "<session-folder>" --push node tools/auto-edl.mjs "<session-folder>" --push node tools/notes.mjs "<session-folder>" --push
Analysis is ready. Generate a first draft with the shared auto-edit engine, then refine it.
Double-click render.cmd in your session folder — no terminal needed. It runs the whole pipeline and writes everything into <folder>/out/:
episode.mp4 — the rendered videoepisode.srt + episode.vtt — captions / subtitlesepisode.mp3 — audio-only exportchapters.txt — YouTube chapter markers (also copyable from the Notes tab)render.cmd runs tools/episode.mjs, which chains the stages (analyze → transcribe → auto-edl → notes → render → captions → audio). Skip a stage with --no-transcribe, --no-notes, --no-render, --no-captions or --no-audio; add --force to re-run stages that are already up to date.
node tools/episode.mjs "<session-folder>"