Podcast clip maker: AI podcast clips that keep both speakers in frame
A two-person podcast is the hardest input an auto-clipper faces: a single centered crop shows the wrong person half the time, or an empty chair. OpenShorts detects a real two-shot and renders both speakers stacked in half-frames, so a reply never happens off screen.
The rest of the pipeline is the same as for any long video: word-level transcription, scene detection, Gemini scoring the 3 to 15 strongest moments, subtitles burned in, and direct publishing to TikTok, Instagram Reels and YouTube Shorts.
Cost is where podcasts punish credit-based tools: they bill the whole episode length before you see a clip. Self-hosted OpenShorts has no meter at all; hosted plans start at $12/month.
First episode free up to 60 minutes, then 20 minutes a month, watermarked, no credit card. No watermark from $12/month, or self-host free under MIT.
What a podcast clip maker does
Podcast clips are the 15 to 60 second moments of an episode that stand on their own: a sharp answer, a disagreement, a story with a punchline, cut to 9:16 with captions for TikTok, Reels and Shorts. A podcast clip maker finds those moments in a full episode for you, reframes them and burns in the subtitles, so one recording becomes a week of posts instead of an afternoon in an editor. The hard part is not the cutting, it is keeping the right people on screen.
Why podcasts break naive clipping tools
Podcast video is a conversation, and conversations move. A tool that crops a fixed center column out of a wide two-shot shows whoever happens to sit in the middle, which is often nobody. A tool that follows one face loses the reaction shots that make clips work. Reviewers of the mainstream clippers consistently report exactly this: framing that needs manual correction on multi-person footage. It is not carelessness, it is that a single moving crop cannot show two people at once.
How the two-speaker layout works
OpenShorts detects when a scene is a genuine two-shot, meaning both faces are visible in the same frame for at least half of the sampled frames. That test matters: it is what separates a real side-by-side conversation from shot/countershot editing, where a naive split would show the same person twice. Confirmed two-shots render as a split layout, both speakers stacked in half-frames filling the 9:16 canvas. With speaker cutting enabled the clip instead hard-cuts to whoever is talking, with mouth activity normalised per speaker so that lighting and contrast differences do not hand the whole scene to one side of the table.
From episode to posted clips, step by step
- Paste the episode's YouTube link or upload the file. Podcasts of an hour or more are the normal case, not the limit.
- faster-whisper transcribes with word-level timestamps, and PySceneDetect maps the cuts.
- Google Gemini reads the transcript against the scene boundaries and returns the 3 to 15 segments that stand alone best, 15 to 60 seconds each.
- Each segment is reframed for its content: split layout for two-shots, face tracking for single speakers, screencast layout if the episode shares a screen.
- Subtitles are burned in from the word-level transcript, and finished clips post directly to TikTok, Instagram Reels and YouTube Shorts, or come back through the API.
The same steps work for any long recording of people talking. Church services are the closest case to a podcast: one speaker for most of an hour, and the sermon clip maker page covers clipping only the sermon and keeping a preacher who walks the stage in frame.
Podcast to TikTok, Reels and Shorts
Video podcast clips are the same file on every platform: vertical, 15 to 60 seconds by default, captions burned in for the people who watch on mute. Connect your accounts once and each clip publishes to YouTube Shorts and Instagram Reels directly. Podcast to TikTok works the same way with one difference TikTok imposes: the clip lands in your TikTok inbox as a draft, and you post it from the app, where you also add the caption and a sound. A week of clips can be scheduled in one go, one a day, so each episode keeps working until the next one is out.
Real podcast clips, next to their source
A two-person episode filmed as one wide shot: both hosts stay in frame, stacked, and the captions sit on the seam.
Real OpenShorts output, not a mock-up. A two-person podcast: both speakers stacked in half-frames, captions on the seam where they cover nobody. Source: Turn the Tables with Dan and Shoshana Jordan, Heritage of Faith, CC BY.
An interview cut between host and guest instead: there is no two-shot to stack, so the crop tracks whoever is on screen.
Real OpenShorts output, not a mock-up. A 39-minute interview: Gemini picked the moment, the crop follows the speaker, and the captions come from the word-level transcript. Source: Startup Founder & CEO Mark Bush on How to Overcome Adversity, Foundation for Economic Education, CC BY.
What a full episode costs to clip
Credit-metered tools bill on the length of the video you import, not on the clips you keep. As of October 2026, a 60-minute episode costs 60 credits at Opus Clip, Vizard or Quso whether it yields 5 usable clips or 20, and a weekly show at that length runs past the entry plans of both. OpenShorts prices the other way around:
Self-hosted, an episode costs nothing to clip: MIT licence, Docker, your own keys, no watermark and no meter, so a two-hour episode costs the same as a ten-minute one. On OpenShorts Cloud your first episode is clipped whole up to 60 minutes for free, then 20 minutes a month with a watermark. After that the unit is the source minute: a 60-minute episode uses 60 of the 100 minutes on the $12/month plan, and a weekly show fits the $29 plan's 300 minutes.
What a weekly show costs to clip, by tool
A weekly one-hour episode is about 260 minutes of source a month. Move the slider to your own schedule:
Cheapest published plan that covers that many minutes, per month. Prices checked 2026-10-05. Self-hosted needs Docker and your own Gemini key, whose free tier covers 1,500 requests a day.
Podcast transcripts
Every episode clipped here is transcribed first, word by word, because that transcript is what the AI reads to find the moments and what the captions are cut from. If what you need is the text of a whole episode rather than clips, and the podcast is on YouTube, the free YouTube transcript generator gives you the podcast transcript from the captions YouTube already has, with timestamps, as TXT or SRT, with no sign-up. Show notes, quotes and an article version of the episode all start from it.
Podcast clips or audiograms: which one do you need?
"Podcast clips" means two different things depending on how the show is recorded. If you record video, even a static two-camera setup, you want vertical 9:16 clips of the speakers with captions, usually 30 to 90 seconds, for TikTok, Reels and Shorts. That is what this page and OpenShorts are about. If the show is audio-only, there is nothing to reframe, and what you want is an audiogram: a waveform and captions over a still image. Audiogram tools such as Headliner serve that case better than any video clipper.
How the podcast clip makers compare
Checked 2026-10-05 on each vendor's pricing page.
| Tool | How it makes podcast clips | Free plan |
|---|---|---|
| OpenShorts | Paste the episode link or upload it; AI picks 3 to 15 moments and keeps both speakers in frame | First video free up to 60 min, then 20 min/month, watermarked; self-hosted unlimited and unwatermarked |
| Riverside | Magic Clips, inside the recording studio | Yes, with a Riverside watermark; Pro ($29/month) removes it |
| Opus Clip | General clipper with a podcast clip maker page | 60 credits/month, watermarked |
| Headliner | Audiograms for audio-only shows, video clipping in beta | One unwatermarked audiogram a month, the rest watermarked |
If you already record in Riverside, its clips come with the recording and that convenience is real. If you record anywhere else, or publish the full episode to YouTube first, a clipper that starts from the link avoids exporting and re-uploading an hour of video.
Common questions
- How do I turn a podcast into clips for free?
- Self-host OpenShorts: clone the MIT-licensed repo, run docker compose up, add a free-tier Google Gemini API key and paste your episode link. No watermark and no cap. If you would rather not run anything, OpenShorts Cloud clips your first episode free up to 60 minutes, then 20 minutes a month, with a watermark; paid plans start at $12/month.
- What is the best podcast clip maker?
- It depends on how you record. For a video podcast with two people on camera, pick a tool that keeps both in frame: OpenShorts stacks them in a split layout when both are visible. If you record in Riverside, its built-in Magic Clips are the most convenient. For an audio-only show, an audiogram tool such as Headliner fits better than any video clipper.
- How does it handle two people talking?
- Scenes where both faces share the frame at least half the time render as a stacked split layout so both speakers stay visible. Optionally it hard-cuts to the active speaker instead, using per-speaker normalised mouth activity to decide who is talking.
- Does it work with hour-long episodes?
- Yes, long-form is the design case. Processing time scales with length: on CPU roughly 5 to 8 minutes of processing per 8 minutes of source, on an NVIDIA GPU about a tenth of that. The AI moment scoring reads the transcript rather than the raw video, so episode length does not degrade selection quality.
- How do I turn a podcast into TikToks?
- Paste the episode link or upload the file, and the clips come back vertical with captions. Send them to TikTok from the dashboard, where each one arrives as a draft in your TikTok inbox to post from the app, or download the MP4s. Reels and Shorts publish directly.
- Can I get a transcript of my podcast?
- Every episode clipped here is transcribed word by word to find the moments and burn the captions. For the text of a whole episode hosted on YouTube, the free YouTube transcript generator returns its captions with timestamps as TXT or SRT, with no account.
Sources
- Competitor per-minute credit billing checked 2026-10-05 on vendor pricing and help pages.
- Split-layout and speaker-cut implementation in the project source at github.com/mutonby/openshorts.