Podcast Clip Maker finds the strongest moments in your episode, keeps the camera on whoever is talking, and reframes everything to 9:16 — then hands you the keyframes, so the final cut is yours. No uploads. No cloud render queue.
Clip tools promise magic and lock you out of the result. We make the first draft — speaker-aware, caption-ready — and keep every framing decision open for you to change.
Transcription, speaker tracking and rendering run locally on Apple Silicon. Your footage never leaves the machine.
Speaker-aware reframing driven by your audio keeps the active host in frame — clip by clip, cut by cut.
Auto-framing is a first draft, not a final answer. Each crop is a keyframe you can drag until it’s exactly right.
Stacked vertical layouts keep both hosts on screen and feature whoever has the mic. More layouts on the way.
A single recording or studio multicam with separate mics — the messier the timeline, the more time you save.
The transcript is indexed once, then mined for moments, hooks and captions. Pick the clips worth posting.
Fix any framing with a keyframe drag, choose a layout, and render 9:16 with hardware encoding.
Your video and audio never leave your Mac. Optional cloud features — like AI-written clip titles — only ever see transcript text, and only if you turn them on. Always disclosed, never the default.
Built with EchoLab, a video-podcast studio in Brussels. Every feature is shaped and stress-tested on real client footage before it ships — not on demo clips.