- Final Cut Pro
- Premiere Pro
- DaVinci Resolve
Multicam podcasts and social clips, cut automatically for Final Cut Pro, Premiere Pro and DaVinci Resolve
podswitch automatically cuts multicam podcast video for Final Cut Pro, Premiere Pro and DaVinci Resolve, using each speaker’s microphone. Add one recording per speaker and it works out who is talking, then returns a project with the timeline already cut and a dialogue mix with mic bleed removed. It also works with a single video-call recording from Zoom, Google Meet or Teams, and with solo talking-to-camera videos. On paid plans it picks the moments most likely to work as short clips and builds them with captions, in vertical, square or landscape, ready in the same editor, with music, thumbnails and posts for each platform on MAX.
Your video stays on your computer. We upload the audio, not the video.
What is podswitch?
podswitch is an automatic multicam podcast editor by Metamindz. Give it one recording per speaker and it works out who is talking from each microphone, then returns a project for Final Cut Pro, Premiere Pro or DaVinci Resolve with every camera switch already made, plus a dialogue mix with mic bleed removed. It also takes a single video-call recording from Zoom, Google Meet or Teams, and solo talking-to-camera videos. On paid plans its Social Studio turns the episode into short captioned clips, a transcript and episode notes, and on MAX adds background music, thumbnails and a post for each platform. Your video stays on your computer: only the audio is uploaded.
- Works with
- Final Cut Pro, Premiere Pro and DaVinci Resolve
- Runs in
- Your web browser, with nothing to install
- Takes
- A mic per speaker, a single video-call recording, or one solo camera
- Uploads
- Audio only. Your video stays on your computer
- You get
- A pre-cut timeline, a bleed-free dialogue mix, a cut list and, on paid plans, captioned social clips, a transcript and episode notes
- Price
- A free plan, Premium from £7.99 a month and MAX at £49.99 a month, including VAT
- Made by
- Metamindz, in London
Edited in your own editor. Without uploading your video.
Tools that edit in the browser need the whole video uploaded first, and keep the edit in their own editor. podswitch needs only the sound from each microphone, and hands the edit to the software you already use. See how it compares.
- No video upload
Your footage never leaves your computer
Your browser pulls the audio out of each camera file on your machine. That audio is all podswitch receives and all it needs: every cut is decided from the microphones. No waiting on gigabytes of 4K, and nothing to hand over.
Measured on our own 2-hour, 2-camera 4K episode: 72.4 GB of video, 349 MB uploaded (207 times less).
- Your editor
Finish in Final Cut Pro, Premiere Pro or DaVinci Resolve
No browser editor to learn and no rendered file you cannot change. Final Cut Pro gets a real multicam clip and a cut timeline, with every switch editable in the Angle Viewer; Premiere Pro and Resolve get a cut timeline with one track per camera. Your effects, grades and templates stay where they are.
Mac or Windows: podswitch runs in the browser, nothing to install.
- The first pass, done
No more switching angles by hand
podswitch syncs every camera by sound, works out who is talking on each mic and makes every cut: the speaker, a listener’s reaction on long answers, the wide when people talk over each other. You start at the fine cut, with a dialogue mix that has the bleed between mics removed.
Pacing presets set how often it switches; change any decision before or after download.
- Social kit
Clips, captions and a transcript from every episode
On paid plans podswitch picks the moments most likely to work as short clips, cuts the pauses, follows the speaker and adds captions in your style, in vertical, square and landscape. They open as projects in your editor, with the transcript as TXT, SRT or WebVTT.
UK studios charge £30 to £39 per social clip (their own price pages, October 2026).
The video from both cameras
72.4 GB
About 8 h 45 min to upload
What podswitch uploaded
349 MB
About 3 min
207 times less
Measured on our own 2-hour episode: 2 cameras, 4K H.264, 25 fps. Upload times at 18.4 Mbit/s, the UK median in Ofcom’s latest home broadband report (March 2023 data), ignoring network overheads.
How does it work?
- 01
Drop in your recordings
For a podcast, one recording per speaker: camera files, a multitrack recorder, or each remote guest’s own track. A single video-call recording or a solo talking-to-camera video works too. Your browser pulls the audio out of each video file, so the video itself never leaves your computer.
- 02
podswitch listens to every microphone
It lines the files up by sound, works out who is speaking on each mic, and decides every cut: the person talking, a listener’s reaction on long answers, or the wide shot when people talk over each other.
- 03
Open the edit in your editor
In Final Cut Pro you get a multicam clip with every angle and a timeline that is already cut: change any decision in the Angle Viewer. In Premiere Pro and DaVinci Resolve you get the cut timeline with each camera on its own track.
How does podswitch choose the camera angle?
It measures the level of every microphone many times a second and compares each one against its own noise floor, so a quiet speaker still registers as speaking. At each moment it asks which microphone clearly leads the others.
- 01
One person talking
Their camera.
- 02
Several people talking
Whoever is clearly louder on their own mic. If nobody leads for a couple of seconds and you have a wide camera, the wide shot.
- 03
Silence
After a pause, a listener, usually the person who spoke before, since they are the likeliest to be addressed.
- 04
A long answer
A short reaction shot of a listener, placed where that listener is not talking, so a single angle never runs too long.
A new voice has to hold the floor for a short moment before the edit switches, and every shot has a minimum length. That is why a quick “mm-hm” does not cause a cut. When a switch does happen, it lands a fraction of a second before the new speaker starts, which is how an editor would time it.
No video frame is ever analysed. The decisions come only from the audio.
New · Calls and solo videos
Also works for video calls and solo videos.
Video-call recordings
Interviews and virtual podcasts recorded as one file from Zoom, Google Meet, Teams and similar. podswitch works out who is speaking from the voices. In gallery view 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, and podswitch tidies the pauses and makes the clips, transcript and captions.
Solo videos
One person talking to camera. podswitch cuts out long pauses with jump cuts and, on paid plans with a transcript, filler words such as “um” and “uh”. It makes clips, captions and a transcript the same way as for a podcast.
Your video stays on your computer. We upload the audio, not the video.
Your browser reads each video file locally and extracts its audio. That audio is all podswitch receives, and all it needs: every decision about who to show is made from the sound. Uploaded audio is deleted automatically when your plan’s retention period ends, and it is never used to train models.
What do you get?
- Multicam clip
- In Final Cut Pro: one angle per camera, plus an audio-only angle carrying the dialogue mix.
- Pre-cut timeline
- Every switch already made: the multicam on a timeline in Final Cut Pro, one track per camera in Premiere Pro and DaVinci Resolve.
- Dialogue mix
- Each mic open only while its speaker talks, so bleed from other mics is removed. AAC by default for small downloads, or 24-bit WAV if you want lossless.
- Jump cuts
- Optional, on every plan: long pauses cut from the edit, every camera and the mix cut at the same frames. On paid plans, with a transcript, filler words such as “um” and “uh” too.
- Cut list
- A CSV of every shot, with start, end and angle, for checking or other tools.
- Preview
- Watch the edit in your browser, played from your own files, before you download anything.
- Social clips
- On paid plans: short clips of the strongest moments, picked by AI with a viral score and the reason for each, with pauses cut, the camera following the speaker and styled captions, in vertical, square or landscape. Open them in your editor, or render an MP4 right in your browser (beta).
- Your logo
- On paid plans: add your logo once and place it on the full edit and every clip, in the MP4s and the editor files.
- Transcript
- On paid plans: the whole conversation with every word matched to its speaker. Download it as plain text, SRT or WebVTT, correct it in the browser, and see the episode’s main themes with a link to each moment.
- Episode notes
- On paid plans: title ideas, a description, YouTube chapters and show notes, drawn from the transcript.
- Team workspace
- On paid plans: invite people by email to share projects and saved settings. The owner pays for the plan.
- MAX extras
- On MAX, the rest of the Social Studio: AI background music under the edit and clips, on its own track in your editor; thumbnails for every clip and the episode in every social size, including AI thumbnails; and post text for LinkedIn, X, Instagram, Facebook, TikTok and YouTube Shorts, with previews and one ZIP. Plus a camera paired with its own mic automatically.
Works with Final Cut Pro, Premiere Pro and DaVinci Resolve
- Multicam clip
Final Cut Pro
A multicam clip with one angle per camera plus an audio angle for the mix, and a timeline with every cut already made. Change any decision in the Angle Viewer. It comes as an FCPXML file: choose File, then Import, then XML.
- Pre-cut timeline
Premiere Pro
A timeline with every cut already made, each camera on its own video track and the mix on the first audio track, on a Mac or on Windows. It comes as an XML file: choose File, then Import.
- Pre-cut timeline
DaVinci Resolve
The same pre-cut timeline, with each camera on its own video track and the mix on the first audio track, on a Mac or on Windows. It comes as an XML file: choose File, then Import, then Timeline.
Social clips open the same way: Final Cut Pro takes the captions as styled titles or plain editable captions, Premiere Pro and DaVinci Resolve get styled text layers or a plain SRT file, and any music sits on its own track. You can also render a clip or the full edit as an MP4 in your browser (beta), with the captions burned in. To show another camera for a shot in Premiere Pro or DaVinci Resolve, trim one clip and extend the neighbouring camera’s clip. After Effects, Avid Media Composer and other editors are not supported. The Final Cut Pro import guide walks through it step by step.
What do you need to record?
The one essential is a separate microphone for each speaker, recorded to its own track or file. Everything else is flexible:
- A camera and a mic per speaker, with each mic recorded into its camera.
- Cameras for picture and a multitrack recorder for the mics. You map each channel to a speaker.
- Extra cameras with no mic, such as a wide shot, added as angles.
- Remote interviews where each participant’s own file is recorded separately.
- A single video-call recording from Zoom, Google Meet or Teams, or one camera for a solo video.
Video files can be MOV or MP4. Audio files can be WAV, AIFF, FLAC, M4A or MP3. You do not need timecode or a clapperboard: podswitch syncs every file by comparing its sound with a reference recording.
The recording guide covers it in more detail.
What does it cost?
Prices in pounds, including VAT.
Free
£0
- 3 projects a month
- Up to 20 minutes per recording
- Audio and mix kept for 7 days
Or try one project without an account, up to 10 minutes long.
Premium
from £7.99 a month
From £7.99 a month, billed monthly or annually, with more projects, longer recordings, advanced pacing, social clips, a transcript, episode notes and your logo.
See all plansMAX
£49.99a month
Everything in Premium plus the rest of the Social Studio: AI background music, thumbnails and AI thumbnails, and posts for six platforms in one ZIP. £499.99 a year if you pay annually.
What MAX addsOne-off
£29.99 once
- One project beyond your plan, without a paid subscription
- Up to 1 hour per recording
- Up to 4 speakers
- Audio and mix kept for 30 days
As listed on usepodswitch.com on 3 November 2026. The current prices are always on its pricing page.
Questions about podswitch
More in the full FAQ.
What does podswitch do?
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.
Does it work with Zoom or Google Meet recordings?
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.
Can I use it for a solo video?
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.
Which video editors are supported?
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.
Do you upload my video?
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.
What do I need to record?
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.
How does podswitch sync my cameras and audio?
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.
How does podswitch remove mic bleed?
In a room, every microphone picks up everyone. podswitch builds a dialogue mix where each speaker’s mic is open only while that person is speaking and turned down while they are not, with smooth fades so the switch is not audible. When two people genuinely talk at once, both mics stay open.
Can I change how often it cuts?
Yes. Every plan includes three pacing presets: Calm, with longer shots for interviews and long-form conversation, Balanced, the default, and Energetic, with quick cuts for lively, fast back-and-forth. Changing the preset re-runs only the decisions, which takes seconds, and never counts as a new project.
Can I change the edit after it is made?
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.
Is my recording used to train AI models?
No. Recordings are processed only to deliver the service to you and are never used to train models.
Do I need permission from my guests?
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 on usepodswitch.com.
How much does podswitch cost?
There is a free plan with 3 projects a month, up to 20 minutes per recording. Premium starts at £7.99 a month, billed monthly or annually; MAX, which adds AI music, thumbnails and the social kit, is £49.99 a month or £499.99 a year; and a single project beyond your plan costs £29.99 once. Prices are in pounds sterling and include VAT. You can also process one recording up to 10 minutes long without an account, using a verified email address.
Who makes podswitch?
podswitch is by Metamindz, a UK technical consultancy and software agency in London. It started as a script that cut a two-speaker podcast for Final Cut Pro, and grew into a product that handles more speakers and extra cameras, syncs every file automatically and makes a bleed-free dialogue mix.
Try it on your next episode.
One free project, up to 10 minutes long, with a verified email address. No account or card needed.
podswitch, by Metamindz
Metamindz is a UK technical consultancy and software agency. We give startups and scale-ups flexible access to CTOs, technical leadership, recruitment and software development, and we make products of our own under the Metamindz Studio name, podswitch among them.
New · Social Studio
One episode. A week of posts.
The Social Studio turns each episode into what you post about it. AI picks the moments most likely to work as short clips and gives each a viral score with its reason. podswitch builds them with pauses cut, the camera on whoever is talking and captions in your style, vertical, square or landscape. On MAX, add background music made for the conversation, thumbnails drawn from your own footage and a post written for each platform.
Short clips cut from your episode for Reels, TikTok, YouTube Shorts and LinkedIn.
Explore the Social StudioSocial clips in detail
Thumbnails made by podswitch from its own sample episode, on MAX.
Short clips, picked by AI
The moments most likely to work as short clips, each with its hook and the reason it was picked. Pauses are cut and the camera follows whoever is talking.
A viral score for every clip
A score out of 100 with a band: High from 80, Good from 60, Fair below. Open it to see what the score weighs. A guide for choosing, not a promise.
Vertical, square or landscape
Every clip in the shape each platform wants, framed on the speaker: 9:16 for Reels, TikTok and Shorts, 1:1 for feeds, 16:9 for YouTube and the web.
Captions in your style
Six starting styles, then make them yours: font, size, colours, outline, a box behind the text and the word being spoken highlighted. Correct any word and set each line’s timing to the millisecond.
Transcripts in every format
The whole conversation, every word matched to the person speaking. Download it as plain text, SRT or WebVTT, correct it in the browser, and jump to each of the episode’s themes.
An MP4, made in your browser
Render any clip or the full edit to an MP4 with the captions burned in, from your own files. The video is never uploaded. In beta.
Music made for the conversationMAX
Three music ideas based on what is actually said, each with a 30-second sample. The track you pick plays quietly under the edit and every clip, dips when someone speaks, and can be moved, trimmed and levelled on the timeline.
Thumbnails, designed or made by AIMAX
Pick the person and the moment, and your browser takes the frame from your camera files: 10 layouts, gradients, photo effects, 9 title fonts and your logo, in every social size. Or describe the design in your own words, and AI makes it from the frames you choose, keeping everyone recognisable.
A post for every platformMAX
LinkedIn, X, Instagram, Facebook, TikTok and YouTube Shorts each get their own post, previewed in the feed with a character count, and quotes checked word for word against the transcript. Download every image and post in one ZIP.
How are social clips made?
podswitch transcribes the episode
As soon as an edit is ready, the dialogue mix is transcribed, with every word matched to the person speaking it.
Claude picks the moments
Tell it how many clips you want, how long, and optionally what to look for. Share them between the speakers on one slider, or pick one of the episode’s themes and get clips about it. It looks for a strong opening line, one clear idea and a payoff that makes sense without the rest of the episode.
podswitch builds each clip
Pauses and dead air are cut out. The camera follows whoever is talking, with short shots of the other person when they react or reply. Captions are timed to the words and laid out for the shape.
You check it, then export it your way
Preview each clip with your own files, change any camera, cut or caption, then download it for Final Cut Pro, Premiere Pro or DaVinci Resolve, or render an MP4 in your browser (beta).
More on the podswitch blog
A real clip, as podswitch built it
These are the suggestions Claude made for one of our own recordings, with the score it gave each. The clip alongside is the top-scored one, built by podswitch from the two camera files. For this page the captions are burned in; in your editor they stay editable.
The score is the model’s judgement of how well a moment stands on its own as a short clip. It does not predict views: what you post, and when, is up to you.
What is in each clip?
Which plans include it?
Social clips come with paid plans. Each plan includes a number of clips per calendar month; a request that fails does not count.
As listed on usepodswitch.com on 3 November 2026.
Social clips questions
What is the podswitch Social Studio?
Everything podswitch makes from an episode for social media, in one place: short clips picked by AI with a viral score, in vertical, square and landscape; background music made for the conversation; thumbnails and social images in every size; and post text for each platform with previews and one ZIP download. It sits alongside the full podcast edit in every project.
What are social clips?
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.
How does podswitch choose the moments?
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.
Are the clips rendered videos?
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.
Are captions included?
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. 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. You can correct every caption, and its timing to the millisecond, before you download.
Can I download the transcript?
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.
What are episode notes?
On paid plans, podswitch writes title ideas, a description, YouTube chapters and show notes for the episode from its transcript.
What happens to my audio for social clips?
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.
Which plans include social clips?
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. Music, thumbnails and the social kit are part of MAX.