rostrum MCP server

rostrum

Clean up talk recordings, from one video to a whole event, by hand or through your agent. rostrum finds redos, retakes, repeats and dead air, shows you every cut with its reason, then renders with ffmpeg and checks the result. Everything runs on your machine.

A 58-second synthetic demo talk. The terminal shows the real output, trimmed to the main lines.

<!-- mcp-name: io.github.girishkvs/rostrum -->

Recording a talk in one take means restarting sentences, slides and clicks. Cutting those by hand takes hours, and one bad join ruins a clip. rostrum proposes each cut with the evidence behind it, you approve or adjust it, and it renders frame-accurate joins and then verifies sync at every join.

Quick start

uv tool install rostrum
rostrum init talk.mp4

pipx install rostrum works too. You also need ffmpeg (winget install Gyan.FFmpeg, brew install ffmpeg, apt install ffmpeg).

init does the whole first pass:

dead air at the start and end, and garbled or untranscribed speech for you to listen to,

1. probes the file (or files) and writes rostrum.json with defaults,
2. transcribes with a local speech engine (the first run downloads the model, about 480 MB),
3. finds cuts: spoken cues ("redo", "stop", "restart"), retakes, repeats, long pauses,

1. writes review.html, where you can play each join, flip keep/cut and nudge edges.

Nothing is cut before you see it.

and importing that file. --yes skips that check.

• rostrum plan lists every cut and the expected length.
• render refuses until the cuts are reviewed: with rostrum decide, or by saving from the page

cut, the newer one wins.

• The page saves -decisions.json. Importing it never undoes a newer decision: for each

• Sources are never modified and outputs are never overwritten.

rostrum plan                       # every cut, its reason, and the expected output length
rostrum decide <cut-id> keep       # or: cut, with --start/--end to move its edges
rostrum decide --import talk-decisions.json   # apply what you saved from review.html
rostrum render                     # frame-accurate render into <talk>.rostrum/renders/render-N/
rostrum verify --mode full         # checks the newest render: frames, audio, decode, A/V sync at every join
rostrum map 23:30 --from render-1  # a time in the edited video -> the source time

Bare rostrum shows the project status, and rostrum doctor checks your setup.

What to expect

These numbers come from one 60-minute single-take talk, run on CPU only (8 cores, small.en):

time, and 95% of what they removed was right to remove. Adding the proposals raised coverage to 90%. Review closes the rest of the gap, which is why it is the default.

• Speed:
• first pass: about 11 minutes;
• render: about 4 minutes;
• full verify: about 1.5 minutes.
• Accuracy: against the speaker's final edit, cuts marked auto covered 69% of the removed

Recording for it

start of the sentence.

• When you fumble, say "redo" (or "stop", "restart"), pause for a second, and restart from the

retake.

• Restarting a slide or a click is fine: the bad attempt and your restart look like any other

• Keep recording. The fewer separate files, the easier the review; several files work as well.

One talk, many files, or a whole event

rostrum init talk-part1.mp4 talk-part2.mp4   # one talk recorded in parts: one timeline, one output
rostrum init talks/                          # one talk per file; *-part1/*-part2 files are grouped

Files join into one talk when their names end in -part1, -part2 and so on (_ or a space works too; set init.partPattern to change it). Every other file is a talk of its own.

Shortened. The full README is on GitHub.