
Find footage faster.
Keep your edit moving.
Your recordings, sessions and saved moments in one reusable library. Find what you need and send it to Resolve Studio or Premiere Pro.
Find dialogue, save moments, and reuse them across projects.Illustrative session · Your original files stay untouched.
Several recordings.
One session to review.
Bring compatible recordings from any folder into one continuous timeline. Mark moments across files and keep those slices ready for every project.
Editor handoff and the full workspace
Use frame stepping and exact in/out points. Send slices to a new timeline or insert them at the playhead. Premiere Pro 26.3 or newer is supported. In Resolve Studio, open a project and set External scripting using to Local in Preferences → System → General.
- Games
- Recordings
- Story
- Sidemissions
- Recordings


Boat chase

Forest Easter-egg

Final fight
IN 0:09:14.300OUT 0:09:20.766Less scrubbing.
More finding.
Search what was said and jump to the right moment. Transcription gets you started. taperat Perception Engine improves the transcript automatically.
- Before
- The harbour record gives us the missing time.
- After
- The harbour record gives us the missing lines.
Corrected using on-screen subtitles.
Diarisation separates voices. OCR supplies character names from subtitles.
How Perception Engine works
Transcription gets you started. taperat Perception Engine is our own system that uses diarisation and OCR to improve your transcript—fixing typos and assigning speakers automatically. All on your computer.
OCR can use character names and dialogue from subtitles. Analysis jobs do not run concurrently.
Your question.
Your footage.
Find a character, a story beat, or that funny moment. Connect your chosen compatible LLM through MCP Bridge, then create slices and tag recordings.
Local processing and your chosen LLM
Transcription and Perception Engine run locally. MCP Bridge runs tools on your computer; if you connect a cloud LLM, its provider handles the data you choose to share.
Find the final fight in my Sands of Orra recording. Save it as a slice and tag the recording “Boss fight”.
Connected to your chosen MCP client
The details, when you need them.
Recording Detection and the in-game overlay
Watch your recording folders, create slices automatically, and name or tag them in taperat’s own overlay. Notifications appear in game, on the desktop and in the app. The overlay uses no game hooks or injection.

Smoother playback with proxies
Generate proxies on demand for smoother seeking. They are stored with your database, while original recordings remain the source.
Folders, tags and source protection
Create folders and subfolders, move recordings and slices freely, and organise moments with nested tags, collections, favourites and ratings. Original recordings stay untouched. Deleted slices remain archived and recoverable; deletion requires two confirmations.
Try it with your own footage.
A free, limited version will also be available for basic needs.
Will it run on my PC?
What you’ll need.
Organising clips takes less power than analysing hours of footage. Here’s a simple guide to choosing your setup.
Organise & clip
Add recordings, create sessions, and save your favourite moments as slices.
- Memory
- 8 GB RAM16 GB if you keep taperat open while gaming.
- Processor
- 4 coresA 64-bit processor. 6–8 cores recommended.
- Free space
- 1 GB + cacheKeep the library and preview cache on an SSD.
A comfortable setup: 16 GB RAM, a 6–8 core processor, and an SSD.
Transcribe & analyse
Transcription makes speech searchable. Perception Engine uses diarisation and OCR to improve the text and assign speakers automatically.
- Memory
- 16 GB RAM32 GB recommended for a comfortable analysis setup.
- Processor
- 6 cores with AVX2AVX2 is a processor feature; check your CPU’s specifications.
- Model space
- 2–4 GB extraAllow 2 GB for models, or 4 GB with the largest speech model.
A comfortable setup: 32 GB RAM and a processor with 8+ cores / 16 threads, plus the library’s storage and playback requirements.
Your recordings can stay put.
A hard drive, external drive, or network storage is fine for your footage. An SSD is recommended for taperat’s library and cache.
Keep your favourite recorder.
Use OBS, ShadowPlay, or your existing recording software. taperat organises the videos they create.
Start with a smaller model.
On a 4-core Windows PC, choose “base” or “small” for transcription. Larger models need more memory and take longer.
What about graphics and 4K footage?
Your graphics hardware should support playback of the format you record in, especially for 4K video. Look for hardware decoding for H.264, HEVC, or AV1 in its specifications.
Windows transcription and OCR use the processor, so an NVIDIA card or CUDA is not required. A compatible Vulkan graphics card can help with speaker separation. For the desktop app, use a 1080p display or higher; 1440p gives you more room.
Do I need an internet connection?
You’ll need it to download speech and analysis models initially; the largest speech model is about 3.1 GB. Once downloaded, transcription and OCR run locally.
For cloud-assisted analysis through MCP Bridge, you’ll also need a compatible MCP client and an internet connection. The cloud model runs with that provider; data you choose to share is handled by them.
These guidelines describe hardware needs. Actual resource use depends on your recordings and the analysis models you choose.