Frequently asked questions

podswitch automatically cuts multicam podcast video for Final Cut Pro, Premiere Pro and DaVinci Resolve, using each speaker’s microphone. You give it one recording per speaker; it works out who is talking from the audio and returns a project with a pre-cut timeline, plus a dialogue mix with mic bleed removed. It also works with a single video-call recording, such as an interview from Zoom or Google Meet, and with solo talking-to-camera videos.

No. Your video stays on your computer. The browser extracts the audio from each video file and uploads the audio, not the video. The only pictures saved are small ones your browser makes: a 128-pixel photo of each speaker, and one small picture per project for your projects list, which you can switch off. If you ask for an AI thumbnail (MAX), the frames you pick and your prompt are sent to make that image. Every decision about who to show is made from the audio. Where podswitch frames a face, such as a person’s tile in a gallery-view call, your browser does it on your computer.

Final Cut Pro, Adobe Premiere Pro and DaVinci Resolve. Final Cut Pro gets an FCPXML file that imports as a multicam clip and a pre-cut timeline. Premiere Pro and DaVinci Resolve get a Final Cut Pro 7 XML file: a pre-cut timeline with each camera on its own track and the mix on the first audio track, on a Mac or on Windows. After Effects is not supported.

For a multicam podcast, one microphone per speaker, recorded to its own track or file. Cameras can record their own audio or you can use a separate recorder: podswitch syncs everything by sound. Extra cameras with no microphone, such as a wide shot, can be added as angles. A single video-call recording or a solo video with one camera also works.

It compares the sound in every file against a reference recording and finds the offset where they line up, then reports how confident it is. If confidence is low, it pauses and lets you nudge the sync by frames before continuing.

Yes. You can rename speakers, swap which camera belongs to whom, choose a different pacing preset or change the microphone mapping. podswitch re-runs only the steps affected, and edits never use up any of your plan’s projects.

Yes, on every plan. Upload the single recording of the call from Zoom, Google Meet, Teams or a similar app. podswitch finds who is speaking by their voice. In gallery view, with each person in a tile, it frames each person from their tile so the edit and the clips show whoever is talking. In speaker view the call already follows the speaker, so podswitch tidies the pauses with jump cuts, and on paid plans makes clips, a transcript and captions.

Yes, on every plan. Choose “Just me talking to camera” for one person and one camera. podswitch suggests jump cuts that remove long pauses, on every plan. On paid plans it can also remove filler words such as “um” and “uh”, which needs a transcript, and makes clips, captions and the transcript.

For the best results, yes: one microphone per person, recorded to its own track or file, lets podswitch tell everyone apart and remove mic bleed from the mix. If you only have a single call recording, podswitch works out who is speaking with speaker detection on the audio instead.

Optional cuts that take long pauses out of the full edit, cutting every camera and the mix at the same frames. They are off by default for podcasts and suggested for solo videos. Removing pauses works on every plan; removing filler words such as “um” and “uh” needs a transcript, so it is on paid plans.

MAX has higher limits, shown on the pricing page, and the Social Studio extras. AI background music: AI suggests three music ideas from the conversation with 30-second samples, and the track you pick plays quietly under the edit and clips, dipping when someone speaks. Move it, trim it and set its level on the timeline; it has its own track in your editor files (tracks carry an invisible watermark and are not exclusive). Thumbnails: designs for every clip and the episode, made in your browser from your own camera frames, with 10 layouts, gradients, photo effects and your logo, in every social size, plus AI thumbnails from a short description. A social kit: post text written separately for LinkedIn, X, Instagram, Facebook, TikTok and YouTube Shorts, with quotes checked word for word against the transcript, feed previews and one ZIP with everything. And camera and mic pairing: a camera file and a separate mic file for the same person are paired automatically, with the clean mic used in the mix.

The folder on your computer where the camera files are, or where you will put them before you open the project. Your browser never tells websites where your files live, so podswitch asks once and writes that folder into the editor file. Put the mix and the other downloaded files in the same folder, and keep the original file names. To copy the path on a Mac, right-click the folder in Finder, hold Option and choose Copy as Pathname; on Windows, hold Shift, right-click the folder in File Explorer and choose Copy as path. The path is optional: without it, you link the files once in your editor.

Your editor could not find a file at the folder path in the project. First check that the camera files, the mix and any music file are all in that folder, with their original names. Then relink once and the editor finds the rest in the same folder. In Final Cut Pro, select the imported event and choose File, Relink Files, Original Media, then Locate All. In Premiere Pro, select the missing clips, right-click, choose Link Media and Locate. In DaVinci Resolve, select the missing clips in the Media Pool, right-click and choose Relink Selected Clips. If the sound drifts, make sure the mix is the one podswitch made for this edit.

Short clips cut from your episode for Reels, TikTok, YouTube Shorts and LinkedIn. podswitch transcribes the conversation, picks the moments most likely to land, cuts out the pauses, switches to whoever is talking, adds captions and frames each clip vertical, square or landscape. You get them as timelines for Final Cut Pro, Premiere Pro or DaVinci Resolve.

An AI model (Anthropic’s Claude) reads the transcript and looks for a strong opening line, one clear idea and a payoff, in a moment that makes sense on its own. Each suggestion comes with its hook, the reason it was picked and a score. The score is the model’s judgement, not a promise of views: you choose what to post.

You choose. Like the full edit, clips open in your editor as timelines that use your own camera files, already cut and framed, with captions you can edit. Or render an MP4 of a clip in your browser (beta): it is made on your computer from your own files, cropped and captioned exactly as in the preview, and your video is not uploaded. In-browser rendering needs a browser that supports WebCodecs.

Yes. Preview each clip with your own files in the browser, rename it, change who is on screen for any shot, add or remove cuts, set the framing for each camera, and make a different person the main focus. You can also ask for clips featuring a particular person.

Yes, in a style you choose: six starting styles and every detail adjustable, from the font and colours to a highlight on the word being spoken. Rendered videos and the preview show the style exactly. Final Cut Pro can take the captions as styled titles or plain editable captions; Premiere Pro and DaVinci Resolve get styled text layers or a plain SRT file. Each editor supports styled text differently, so the SRT is always available. You can correct every caption, and its timing to the millisecond, before you download.

The dialogue mix is transcribed by AssemblyAI in the EU, and the transcript, with the speaker names you entered, is sent to Claude to choose the clips. Neither may use it to train their models. Your video is never uploaded.

Yes, on plans with social clips. Download it as plain text with speaker names, or as SRT or WebVTT subtitles for the whole episode. You can correct it in the browser first, or replace it with your own SRT or VTT file. Corrections are used for themes and new clips.

On paid plans, podswitch writes title ideas, a description, YouTube chapters and show notes for the episode from its transcript.

Paid plans. Each plan has a number of clips per calendar month, shown on the pricing page. Clips made by a request count against it; a request that fails does not.

On MAX, podswitch suggests three music ideas from what is said in the episode. Hear a 30-second sample of each, then make a full track of the one you like. It plays quietly under the full edit and the clips and dips when someone speaks. Move it, trim it and set its level on the timeline, and it arrives as its own track in your Final Cut, Premiere Pro or Resolve files. The music is made with AI, carries an invisible watermark and is not exclusive to you.

Yes. You pick the person and the moment, and your browser takes the frame from your own camera files and draws the design: 10 layouts, solid colours, gradients, photo effects, 9 title fonts, everyone in one image if you like, and your logo. Nothing is uploaded for these. AI thumbnails are different: you describe what you want, and the frames you choose and your words are sent to our image provider to make the design.

A post for each of LinkedIn, X, Instagram, Facebook, TikTok and YouTube Shorts, written separately for how each platform is read, with a preview of how it looks in the feed and a count against the platform’s character limit. Anything in quotation marks is checked word for word against your transcript; a quote that does not match loses its quotation marks. The episode also gets a description, chapters and title ideas.

Yes. The full kit is one ZIP with a folder for the episode and each clip: every image size you picked, in each design you chose, your AI images and a text file with the post for each platform. Clips download as timelines for your editor or as MP4s rendered in your browser (beta).

Yes, on paid plans. Upload a PNG, JPEG, WebP or SVG once, then place, turn and resize it on the preview, with its own spot for each shape. It appears in the full edit, the clips, the MP4s you render and the editor files, and on MAX in the thumbnails too.

Short clips, captions, transcripts and the logo come with every paid plan, each with a number of clips per month. Background music, thumbnails, AI thumbnails and the social kit are part of MAX. The pricing page has the current prices and limits.

Your browser compresses the audio before uploading it: each microphone becomes its own Opus stream at 96 kbps, which keeps speech clear and makes uploads several times smaller. Channels that are silent for the whole recording are left out. On paid plans you can choose a lossless upload instead.

No. Recordings are processed only to deliver the service to you and are never used to train models.

Uploaded audio is deleted automatically 1 day after it finishes uploading on the free plan and the free trial, and 14 days after on paid plans. Each new edit of the project starts that period again. The rendered mix is kept for 1 day after a free trial, and for your plan’s retention period for members (7 days on the free plan). Project details and cut lists are kept until you delete the project or your account.

Yes. By uploading a recording you confirm that everyone whose voice is in it has agreed to it being processed. For recordings, podswitch acts as a processor on your behalf; see the privacy notice and acceptable use policy.

Yes. You can process one recording free with a verified email address, without creating an account, up to 10 minutes long. The files from a trial are kept for 1 day.

One recording session. Its length is measured by its longest source file. Editing a project and re-processing it afterwards is free and does not count as another project.

Yes. All prices are in pounds sterling and include VAT at the applicable rate.

From your account, open Billing and choose Manage billing. Cancellation takes effect at the end of the current billing period, and you keep your paid limits until then. After that your account moves to the free plan.

Files you already have stay available until the expiry date they were given when they were made. Your new plan’s limits apply to projects you create after the change takes effect.

A single purchase that unlocks one project beyond your plan’s limits, for example a recording that is longer than your plan allows. You need an account to buy one.

Your statutory rights are not affected. The cancellation and refunds page explains how cancellation works and when the 14-day cancellation period applies to digital services that start straight away.