Report 01 of 09All work
Live stream clipping / Built, in launch preparation

Vertreel

Watches a live stream, finds the moment worth keeping and renders it as a captioned vertical reel.

Python 3.12ffmpegWhisperOllamayt-dlpDockerStripe
Fig. 1 / Vertreel in use
3
platforms watched: Twitch, YouTube, Kick
90 s
learning period before a stream can trigger a clip
12
maximum clips per hour, per stream
4
plans, from free to studio

01Summary

Vertreel watches live streams, detects highlight moments and renders captioned 9:16 reels, each with a title, description and tags ready to paste for every platform. In public mode it needs only a channel link. The creator does not have to log in.

It is a multi-tenant web app that also installs on a phone. Workspaces have their own streams, clips, visual style and plan, and one watched stream is recorded and analysed once however many workspaces follow it.

02Why I built it

A stream runs for hours and the part worth sharing lasts thirty seconds. Finding it by hand means watching everything twice. I wanted the detection to come from the audience itself: the chat and the audio already tell you when something happened.

03How it works

  1. Step 1

    Watch

    Follow the stream and its chat. Learn what normal looks like for this particular channel.

  2. Step 2

    Detect

    Three signals: chat speed against the stream's own baseline, many different chatters using clip, laugh or hype words, and sudden loudness.

  3. Step 3

    Judge

    Transcribe the best candidates and have a local model rank them. Audio-only moments must clear a higher bar.

  4. Step 4

    Cut

    Snap the start and end to sentence boundaries so a clip never opens mid-word.

  5. Step 5

    Render

    Crop to vertical following the action, add captions, facecam or B-roll layout, watermark.

  6. Step 6

    Write

    Draft the title, description and tags for each platform.

Fig. 2Videos readable out of 12, by where the request came from

Measured while building the learning loop. From a datacentre address YouTube asked every request to sign in. I did not try to evade it. Collection moved to my own machine and only the feature rows are synced to the server.

04Decisions

DecisionReason
Free by defaultCopy is written by a local model first, then free tiers, then a plain template. A paid model is used only if switched on.
One chatter counts at most twiceA single excited viewer should not be able to trigger a clip alone.
Creative Commons B-roll onlyThe licence field is verified. A title that says no copyright is ignored. The source is credited on the video and in every post.
A small ranker, not fine-tuningThe learning loop is a logistic regression checked on held-out videos. Its labels are proxies for views, and the documentation says so.

05What broke

06What is next

Payments review and a first round of real users.

Hire meBook a call