Podcast Clip With Two Speakers

A podcast clip with both speakers stacked in a split screen and captions.

Pipeline: Basic edit (cut): cuts, captions, looks, speed, split screens, stock, voices and music.
Format: 9:16
Upload: The two camera files of the podcast (one per speaker), or one wide shot of both.

The prompt

Type your own words into the fields: the [BLANKS] fill in as you go. Copy it and send it to Claude or ChatGPT with Cut Express connected.

Prompt

I uploaded a podcast episode with [GUEST NAME] and me. Inspect it with a transcript and moments, and find the best [LENGTH IN SECONDS]-second exchange about [TOPIC].

- 9:16 split screen in rows: the person speaking on top, the other below, with a 12 px gap. Switch who is on top when the speaker changes.
- If there is only one wide shot, crop each person out of it into their own cell.
- Captions from the speech in the middle, between the two rows: clean preset, highlight [CAPTION COLOR].
- A lower third for [GUEST NAME] in the first 3 seconds with "[GUEST TITLE]".
- Clean both voices: denoise and enhance.
List the candidate exchanges with their times before rendering.

The blanks

[GUEST NAME]: Your guest's name, as it should appear on screen.
[LENGTH IN SECONDS]: How long the finished video runs, as a number of seconds. Reels and Shorts hold best between 15 and 60.
[TOPIC]: What the video is about, in one sentence.
[CAPTION COLOR]: The color of the highlighted word in the captions, as a name or a hex code like #FFD23F.
[GUEST TITLE]: One line under the name, for example "Founder of Lumen".

Tips

Ask for the exchange, not the monologue. A question and its answer makes a clip people finish.
Cropping two people out of one wide shot works best when the shot is 4K or at least 1080p.

New to prompting video? How to write a good prompt for Cut Express covers the story, the hook, captions, sound, pace and how to iterate with versions.

Paste it in Claude. Get the MP4.

Start your 7-day free trial Or get the Mac app

7 days free, then $19/mo. Cancel before day 7 and you pay nothing.

Basic edit9:16

Talking Head With Jump Cuts

A tight talking-head video with the silences cut, punch-ins and captions.

Upload: One or more takes of you talking to the camera.

I recorded a talking-head video about [TOPIC]. Inspect it with a transcript and use the speech cuts.

- Keep only the best take of each sentence and cut every silence and "um". The finished video is about [LENGTH IN SECONDS] seconds.
- Start on "[HOOK LINE]" even if I said it later.
- A punch-in zoom (about 1.2x) every 2 or 3 cuts, on the words that matter, so it never looks like one static shot.
- Captions: bold preset, upper case, 2 to 3 words per line, highlight [CAPTION COLOR], just under the middle of the frame.
- Clean my voice: denoise 40 and enhance. [LOOK] look, a little sharpening.
Show me the timeline (each kept line with its time) before you render.

Fill in Tips

Motion graphics9:16

Audio Podcast Clip With Moving Sound Bars

An audio-only podcast clip with sound bars that move with the voice.

Upload: The episode's audio file and its cover art (a photo or image).

Make a [LENGTH IN SECONDS]-second clip from my podcast audio, [SHOW NAME]. Inspect the audio with a transcript and pick the line that works best on its own about [TOPIC].

- Picture: my cover art large in the top half on a [BACKGROUND COLOR] background, a slow zoom in over the whole clip.
- Under it, a motion graphic of 24 sound bars that follow the real voice (levels from the mix), in [CAPTION COLOR].
- Captions from the speech under the bars: karaoke preset, 4 words per line.
- The show name and episode number as a small label at the top.
Show me the timeline before you render.

Fill in Tips

Basic edit9:16

Shorts From One Long Video

Several vertical Shorts cut from one long video, each with captions.

Upload: One long video with speech (a podcast, a talk, a stream, a course lesson).

I uploaded [LONG VIDEO], about [TOPIC]. Inspect it with moments and a transcript, then find the [NUMBER OF CLIPS] strongest moments that make sense on their own, each about [LENGTH IN SECONDS] seconds.

Before you render, list them for me: the in and out times, the first line said and why it works as a hook. Wait for my pick.

For each one I pick:
- Start on the hook line, no warm-up. Cut the silences and the false starts on the speech.
- 9:16, cover crop kept on the speaker's face. A slow punch-in on the key sentence.
- Captions from the speech: bold preset, 3 words per line, the key word in [CAPTION COLOR], bottom third.
- Clean the voice (denoise and enhance). No music unless I ask.
Render each as its own video titled "[SERIES NAME] 1", "2", and so on.

Fill in Tips