Claude Code can make videos: it records the app, narrates with ElevenLabs, and syncs audio to video automatically

A solo developer used Claude Code, an agentic coding tool, to automatically produce a narrated product demo video for ClinTrialFinder, a free clinical-trial matching tool for cancer patients. The agent drove a live web app via Playwright, synthesized a voiceover with ElevenLabs, and synced narration to on-screen actions using timestamped beats and ffmpeg, eliminating manual screen recording and video editing. The developer says the approach is generalizable to any web app.

I'm a solo builder. I needed a 2-minute product demo for ClinTrialFinder https://clintrialfinder.info — a free tool I built that matches cancer patients to clinical trials. I can fumble through OBS and iMovie, but I'm not proficient — and Claude Code does it faster. So I asked Claude Code — an agentic coding tool — to make it. And it did: a narrated walkthrough where the voiceover lands exactly on the on-screen action. I never opened a screen recorder. I never opened a video editor. I never manually lined up a single caption to a single frame. Here's the video it produced https://www.youtube.com/watch?v=gbVJLpa22Io . This post is about the three things the agent did to make it — because I think that combination is new. Instead of me screen-capturing a session by hand, the agent wrote a Playwright script that drives the real, live web app : it opens the site, fills out the 10-step patient wizard with a synthetic case, submits, and records the finished results page — all headless, straight to video. That means no manual take, no re-shooting when I fumble a click, no "oops the mouse jittered." The recording is code , so it's deterministic and repeatable. When the product changes, the agent re-runs the script and out comes a fresh clip. It even injected a fake cursor that glides between elements, because a headless recording has no real mouse pointer. I didn't record a voiceover. The agent wrote the narration script, then called the ElevenLabs text-to-speech API to synthesize it in a clean, consistent voice. If I want to change a line, it edits the text and regenerates that clip in seconds — no re-recording, no "let me find a quiet room," no matching my tone across takes. js // the agent calls ElevenLabs per narration phrase const res = await fetch https://api.elevenlabs.io/v1/text-to-speech/${VOICE} , { method: 'POST', headers: { 'xi-api-key': KEY, 'Content-Type': 'application/json' }, body: JSON.stringify { text, model id: 'eleven multilingual v2' } , } ; This is the part that normally needs a human in a video editor, dragging clips around a timeline until the words match the picture. The agent did it automatically , and this is the genuinely clever bit: While recording, it logs the timestamp of every key on-screen moment — the submit click, the results appearing, a trial opening, the "copy to AI" dropdown. js const beat = name = console.log BEAT ${name} @ ${elapsed }s ; // BEAT submit-click @ 46.83s // BEAT results-shown @ 68.73s // BEAT trial-open @ 90.17s Then it cuts the narration into phrases, one per beat, and places each phrase at its beat's timestamp in the final mix ffmpeg 's adelay . The result: when the voice says "now it goes to work," the button is being clicked; when it says "open any trial," the trial is opening. The sync falls out of the recording itself — no dragging, no eyeballing, no manual alignment. Making a product demo used to mean: screen-record a take, write a script, record a voiceover, then sit in an editor syncing them. Four manual steps, each needing a skill or a person . Here it was one conversation with an agent . The whole pipeline is code — record → narrate → align → assemble — so it's: The agent also quietly handled the fiddly parts I'd never want to — a site that won't render headless screenshot + Ken Burns instead , audio mixing that silently halves volume, a blank loading frame that throws off the timing. I didn't debug any of it; it did. The shift, for me, is that making a demo video is now something you ask for, not something you produce. The example here is my own project — ClinTrialFinder https://clintrialfinder.info , a free clinical-trial matching tool for cancer patients — but nothing about the approach is specific to it. If you have a web app and an agent, you can have a narrated, synced demo without touching a recorder or an editor.