Problem[01]
Is that what she said?
The quote is in your notes, but the desk wants it checked against the recording. That means scrubbing an hour-long interview for one sentence while the deadline gets closer.
For Journalists and newsrooms
Find the exact quote before you file
Interviews, press conferences and phone video from the scene, transcribed on your Mac without uploading a second of audio. Ask what was said and get the line, the clip and the timecode.
14 days free, then $59 a year or $7.99 a month. Works with your Claude or ChatGPT plan; timelines need DaVinci Resolve Studio 21.1+. Clip descriptions are optional and use your own API key, billed by Anthropic or OpenAI.
Works withA Mac with Apple silicon · macOS 26+
ClaudeClaude Desktop and Claude Code
ChatGPTThe ChatGPT Mac app and Codex
DaVinci Resolve Studio 21.1Timelines through its own MCP server
Any drive or NASThe Prewatch folder travels with the media
Problems
What slows Journalists and newsrooms down
Problem[02]
Footage from everywhere
Your phone, the photographer's camera, a stringer's card. Different devices, files named IMG_4821, nothing labeled, and the package has to be cut within the hour.
Problem[03]
Tape you can't upload
An anonymous source, a whistleblower, an interview under embargo. Some tape can't go to a transcription website, and transcribing by hand takes longer than the story allows.
What Prewatch gives you
Your footage, already watched
Prewatch indexes every clip on your Mac, so Claude or ChatGPT knows what is in your footage and can build the cut with you in DaVinci Resolve Studio.
| What you get | Where it runs | What it does for you |
|---|---|---|
| Transcription on the Mac | On your Mac | Whisper on the Mac's GPU detects the language spoken and transcribes it. No audio or video leaves the Mac to be transcribed. |
| Every line timed, doubts marked | On your Mac | Each line keeps its seconds and timecode. Lines the recognizer was unsure of are marked, so you play those moments before you quote them. |
| Reporter and source apart | On your Mac | Voices told apart within each clip and recognized across clips, on your Mac. Nobody is named unless you name them, voiceprints never leave the Mac, and names are never sent to a model. |
| Locations stay with you | On your Mac | Read from the file as coordinates with no network lookup and never sent to a description model. Recording them can be switched off for sensitive work. |
| Translation that keeps names | Claude or OpenAI | Interviews in other languages translated line by line with your own Claude or OpenAI API key, times kept, names never invented. Without a key, Whisper translates on the Mac, rougher. |
| Search across all of it | On your Mac | One search for a name, a place or a phrase across every indexed folder: interviews, press conferences and scene video. |
Prewatch · ClipsMac app
The screenshot arrives with the app
Ask it
One question instead of a day of scrubbing
You ask in Claude or ChatGPT. Prewatch answers with the clips, the seconds and the timecode, and your assistant builds the timeline in DaVinci Resolve Studio.
01
What exactly did the minister say about the budget at the press conference?
The lines word for word as transcribed, with the clip and timecode, and any line marked unsure, so you check the audio.
Your AI app02
Find the phone footage from the scene shot after 6 p.m.
The clips by capture time from every device, what each shows when descriptions are on, and which are steady enough to use.
Your AI app03
Cut a 90-second package from the interview and scene footage.
A timeline in DaVinci Resolve Studio with the key quotes in order and scene footage between them, ready for your edit.
Your AI appIs anything uploaded when I transcribe?
No. Transcription and speaker detection run on your Mac, and no audio or video leaves it. When you ask Claude or ChatGPT, what Prewatch answers, including transcript lines, becomes part of that conversation under your account, so keep the most sensitive tape out of those questions.
Can I rely on the transcript for quotes?
Treat it as a model's hearing, not a record. Lines Whisper was unsure of are marked and every line has its time, so you can play the exact moment before you quote it.
Does it identify the people in my footage?
No. There is no face recognition. Voices are told apart and the same voice is recognized across clips, from voiceprints kept only on your Mac (you can turn this off, or delete them, in Settings). Nobody is named unless you name them, and names are never sent to a description model.
Does it work with the free version of DaVinci Resolve?
Building timelines by chat needs DaVinci Resolve Studio 21.1 or later, whose built-in MCP server lets your assistant work in Resolve. With the free version you can still index your footage, search it and ask Claude or ChatGPT about it, then place the clips yourself. A file handoff that the free version can import is planned.
How does the free trial work?
Prewatch is an App Store subscription with a 14-day free trial: $59 a year or $7.99 a month after it. You manage or cancel it in your Apple Account's subscription settings; cancel before the trial ends and you are not charged.
Try it on your own footage
Point Prewatch at a folder you have already shot, then ask about it in Claude or ChatGPT.
14 days free, then $59 a year or $7.99 a month. Works with your Claude or ChatGPT plan; timelines need DaVinci Resolve Studio 21.1+. Clip descriptions are optional and use your own API key, billed by Anthropic or OpenAI.