# Jumper Docs

> Documentation for Jumper: local AI video tagging, footage search, video analysis, and agentic video editing for Premiere Pro, Resolve, Avid, and Final Cut Pro.

- [Jumper Documentation](https://docs.getjumper.io/index.md): Use Jumper to search visual content, dialogue, and people locally across analyzed footage in Premiere Pro, Resolve, Avid, Final Cut Pro, or Standalone.
- [Install Jumper and search your footage](https://docs.getjumper.io/quickstart.md): Install Jumper, connect Adobe Premiere Pro, Final Cut Pro, DaVinci Resolve, or Avid Media Composer, analyze footage, and run your first search.
- [Interface](https://docs.getjumper.io/interface/interface.md): Learn about the Jumper interface
- [Jumper integrations for video editing software](https://docs.getjumper.io/NLE/nle_integrations.md): Use Jumper's local AI footage search directly inside Adobe Premiere Pro, Final Cut Pro, DaVinci Resolve Studio, and Avid Media Composer.
- [Jumper compatibility and system requirements](https://docs.getjumper.io/compatibility.md): Check Jumper compatibility and system requirements for Adobe Premiere Pro, Final Cut Pro, DaVinci Resolve Studio, and Avid Media Composer.
- [Video tutorials](https://docs.getjumper.io/tutorials/videos.md): Learn how to use Jumper with these tutorial videos.
- [Frequently Asked Questions](https://docs.getjumper.io/faq.md): Answers about Jumper installation, licensing, privacy, offline AI footage search, supported editing software, media analysis, and performance.
- [Report an issue](https://docs.getjumper.io/report.md): Learn how to get help when Jumper isn't working as expected
- [Analyzing media](https://docs.getjumper.io/core-concepts/processing.md): Analyze footage locally to create separate searchable data for AI video tagging, automated logging, visual search, speech, faces, and summaries.
- [AI Video Analysis, Understanding, and Tagging](https://docs.getjumper.io/core-concepts/ai-video-analysis.md): Learn how Jumper analyzes and automatically indexes visual content, speech, people, summaries, and technical metadata without manual video tagging.
- [Visual search](https://docs.getjumper.io/core-concepts/visual-search.md): Search analyzed visual content with text or reference images and return continuous query-matching scenes with precise source start and end times.
- [Speech search](https://docs.getjumper.io/core-concepts/speech-search.md): Find spoken words, label speakers, and open search results in the full transcript
- [Face detection](https://docs.getjumper.io/core-concepts/face-detection.md): Detect and identify people in your footage
- [Summary Analysis](https://docs.getjumper.io/core-concepts/summary-analysis.md): Create layered, navigable descriptions of long-form footage for editorial research, source-range discovery, and agentic video-editing workflows.
- [Machine Learning](https://docs.getjumper.io/core-concepts/machine-learning.md): Understanding how Jumper uses AI models to search, transcribe, recognize people, and summarize footage
- [Local and Offline](https://docs.getjumper.io/core-concepts/data-sovereignty.md): Everything runs on your device. Your footage never leaves your computer.
- [Agentic video editing with Jumper](https://docs.getjumper.io/core-concepts/agentic-editing.md): Agentic video editing lets compatible AI agents use Jumper to analyze, search, review, and assemble footage through a local MCP server.
- [Agentic editing and data privacy](https://docs.getjumper.io/core-concepts/agentic-editing-privacy.md): What the agent receives via MCP and how model providers handle it
- [Licensing](https://docs.getjumper.io/core-concepts/licensing.md): About Jumper licenses
- [Jumper Standalone: search footage without an NLE](https://docs.getjumper.io/standalone-app.md): Use Jumper without opening an NLE to analyze and search footage locally, manage media, and export visual or speech results as subclips or CSV.
- [Jumper for Adobe Premiere Pro](https://docs.getjumper.io/NLE/premiere/premiere-index.md): Use Jumper's local AI footage search inside Adobe Premiere Pro on macOS or Windows, then open results, mark ranges, and add clips to a sequence.
- [Fix the Jumper panel not opening in Premiere Pro](https://docs.getjumper.io/NLE/premiere/premiere-panel-not-opening.md): Reinstall the Jumper extension when its panel does not appear under Window > Extensions in Adobe Premiere Pro on macOS or Windows.
- [Jumper for Final Cut Pro](https://docs.getjumper.io/NLE/fcp/fcp-index.md): Install and use Jumper's local AI footage search as a Final Cut Pro workflow extension on macOS, with visual, speech, and people search.
- [Install Jumper for Final Cut Pro](https://docs.getjumper.io/guides/fcp-guide.md): Install the Jumper workflow extension for Final Cut Pro, grant its required macOS permissions, open it in FCP, and configure Paste Timecode.
- [Jumper for DaVinci Resolve Studio](https://docs.getjumper.io/NLE/resolve/resolve-index.md): Install and use Jumper's local AI footage search in DaVinci Resolve Studio on macOS or Windows. The paid Studio edition is required.
- [Install Jumper for DaVinci Resolve Studio](https://docs.getjumper.io/NLE/resolve/resolve-guide.md): Install Jumper for DaVinci Resolve Studio on macOS or Windows, enable external scripting, open the integration, and verify required shortcuts.
- [Jumper for Avid Media Composer](https://docs.getjumper.io/NLE/avid/avid-index.md): Install and use Jumper's local AI footage search in Avid Media Composer on macOS or Windows, including MXF and linked or AMA media workflows.
- [Install Jumper for Avid Media Composer](https://docs.getjumper.io/NLE/avid/avid-guide.md): Install the Jumper panel for Avid Media Composer on macOS or Windows, open it from Avid, load media, and configure required shortcuts.
- [Add Avid Media Composer media to Jumper](https://docs.getjumper.io/NLE/avid/avid-adding-media.md): Load Avid clips into Jumper using the correct workflow for transcoded MXF media or linked and AMA clips, including multi-machine metadata setup.
- [Troubleshoot Jumper for Avid Media Composer](https://docs.getjumper.io/NLE/avid/avid-troubleshooting.md): Fix a missing Jumper panel, media-linking failures, broken Mark IN or OUT actions, shortcut conflicts, and MXF metadata scan problems in Avid.
- [Search best practices](https://docs.getjumper.io/guides/search-best-practices.md): Tips and tricks for getting the best search results in Jumper
- [Search all analyzed media across projects and drives](https://docs.getjumper.io/guides/manage-search-context.md): Choose which files Jumper searches, or search every analyzed file across projects and connected or disconnected storage drives from one place.
- [Tag collections](https://docs.getjumper.io/guides/tag-collections.md): Create personal or shared Tag Collections to save video segments or whole clips, add comments and color markers, filter search, and revisit selects.
- [Script Editor](https://docs.getjumper.io/guides/script-editor.md): Open a file’s full transcription in Jumper, edit the script view, send segments to the timeline, and export
- [Using face detection](https://docs.getjumper.io/guides/face-detection.md): Step-by-step guide to detecting faces, naming people, and searching for them in your footage
- [Create a Summary](https://docs.getjumper.io/guides/create-summary-analysis.md): Run a Summary Analysis on selected footage and explore the layered result
- [Your first agentic editing export](https://docs.getjumper.io/tutorials/agentic-editing.md): Export clips from Jumper using an AI agent in a few simple steps
- [Local Agentic Editing with Jumper and LM Studio](https://docs.getjumper.io/guides/lm-studio.md): Set up fully local agentic editing in Jumper using LM Studio and a free open source local model.
- [Add a custom skill](https://docs.getjumper.io/guides/add-custom-skill.md): Define a repeatable agent workflow for your team's export defaults
- [Overcutting with Jumper](https://docs.getjumper.io/guides/overcutting.md): Use Jumper to replace specific shots in your timeline with high-resolution source media
- [Shared Analysis](https://docs.getjumper.io/guides/shared-analysis.md): Set up shared analysis folders on networked drives to use Jumper across multiple devices and share analysis data between users
- [Watch Folders](https://docs.getjumper.io/guides/watch-folders.md): Automatically analyze new media added to selected folders for AI video tagging, visual search, speech search, face detection, and summaries.
- [Custom License Server](https://docs.getjumper.io/guides/custom-license-server.md): Configure Jumper to authenticate against an on-premises license server for air-gapped environments
- [Uninstall Jumper](https://docs.getjumper.io/guides/uninstall.md): A step-by-step guide to uninstalling Jumper
- [Search footage across projects with Jumper](https://docs.getjumper.io/interface/search-tab.md): Use visual, speech, and people search in the current project or across every analyzed file, including media on disconnected storage drives.
- [Media tab](https://docs.getjumper.io/interface/media-tab.md): The Media tab is where you manage the media files that Jumper has access to
- [People tab](https://docs.getjumper.io/interface/people-tab.md): Learn about the People tab in Jumper
- [Settings tab](https://docs.getjumper.io/interface/settings-tab.md): Configure Jumper in the Settings tab
- [Supported file formats](https://docs.getjumper.io/reference/supported-file-formats.md): Complete list of file formats that Jumper can analyze
- [Supported Languages](https://docs.getjumper.io/reference/supported-languages.md): Languages supported by Jumper's speech search
- [List of Machine Learning Models](https://docs.getjumper.io/reference/machine-learning-models.md): Models Jumper uses for local visual search and speech transcription
- [System Requirements](https://docs.getjumper.io/reference/system-requirements.md): Complete system requirements for Jumper across all platforms and NLEs
- [Crash logging](https://docs.getjumper.io/reference/crash-logging.md): How Jumper reports crashes with Sentry and how to turn it off
- [Unable to search](https://docs.getjumper.io/common-issues/select-media-before.md): If Jumper won't let you search there can be a few different things to check
- [Panel won't open](https://docs.getjumper.io/common-issues/panel-not-opening.md): If you have trouble opening the Jumper panel, select your NLE for platform-specific troubleshooting.
- [Known Issues](https://docs.getjumper.io/common-issues/known-issues.md): A list of known issues with Jumper.
- [macOS](https://docs.getjumper.io/release-notes/macos.md)
- [Windows](https://docs.getjumper.io/release-notes/windows.md)
- [Developers](https://docs.getjumper.io/developers.md): Build custom tools on top of Jumper's local analysis and search using the Public API or AI agents.
- [Your first Jumper app](https://docs.getjumper.io/developers/your-first-app.md): Build a small local app that connects to the Jumper API and returns search results.
- [Public API](https://docs.getjumper.io/developers/api.md): Build local media-analysis and video-search integrations with the Jumper Public API, generated endpoint reference, and canonical OpenAPI files.
- [Jumper Public API](https://docs.getjumper.io/api-reference/introduction.md): Overview of the Jumper Public API v1, with direct links to the canonical OpenAPI YAML and full Markdown reference for agents and integration tooling.
- [API Spec Files](https://docs.getjumper.io/api-reference/spec-files.md): Raw download links for the Jumper Public API v1 OpenAPI YAML, OpenAPI JSON, and Markdown endpoint reference.
- [Public api v1](https://docs.getjumper.io/api-reference/public-api-v1.md)
- [Health check](https://docs.getjumper.io/api-reference/health/health-check.md): Returns server status. No authentication required.
- [Get currently loaded models](https://docs.getjumper.io/api-reference/models/get-currently-loaded-models.md): Returns the visual and speech analysis models that are currently loaded in memory.
- [List available models](https://docs.getjumper.io/api-reference/models/list-available-models.md): Returns all supported models for this platform, which ones are downloaded, and which is currently loaded.
- [Switch the active visual model](https://docs.getjumper.io/api-reference/models/switch-the-active-visual-model.md): Loads a different visual analysis model. The model must already be downloaded. This clears loaded analysis data from memory — you will need to reload it afterwards.
- [Get metadata for media files](https://docs.getjumper.io/api-reference/media/get-metadata-for-media-files.md): Returns properties (duration, FPS, timecode) and analysis status for each media file. Use this to check which files have been analyzed and to get their `hash_str` identifiers.
- [Start media analysis](https://docs.getjumper.io/api-reference/analysis/start-media-analysis.md): Starts an asynchronous analysis pipeline. Returns immediately with a `task_id` that can be used to track progress via SocketIO.
- [Cancel running analysis](https://docs.getjumper.io/api-reference/analysis/cancel-running-analysis.md): Requests cancellation of any currently running analysis task.
- [List hierarchical summary collections](https://docs.getjumper.io/api-reference/summaries/list-hierarchical-summary-collections.md): Returns compact collection metadata and counts without enumerating members by default. Pass collection_id with include_members=true to return every compact registry member of only that collection, without loading summary text or applying the legacy 500-member cap.
- [List named summary analyses for media](https://docs.getjumper.io/api-reference/summaries/list-named-summary-analyses-for-media.md): Lists selected media only. With neither media_paths nor hash_strs, returns an empty summaries array. Reads persisted artifacts directly; analysis data does not need to be loaded.
- [Read a compact whole-media summary](https://docs.getjumper.io/api-reference/summaries/read-a-compact-whole-media-summary.md): Returns one selected root node plus bounded previews of its immediate children. Reads persisted artifacts directly; analysis data does not need to be loaded.
- [Drill into one hierarchical summary node](https://docs.getjumper.io/api-reference/summaries/drill-into-one-hierarchical-summary-node.md): Returns one selected node and its immediate children. Node IDs are local to an analysis, so keep summary_ref on every request. Leaf evidence is included only when requested.
- [Load all analysis data into memory](https://docs.getjumper.io/api-reference/analysis-data/load-all-analysis-data-into-memory.md): Loads all visual analysis data, people metadata, and transcriptions from the analysis folder into memory. Must be called before searching, unless you use `/analysis-data/load-for-media` instead.
- [Load analysis data for specific media files](https://docs.getjumper.io/api-reference/analysis-data/load-analysis-data-for-specific-media-files.md): Selectively loads visual analysis data for the given video or image files only. More efficient than loading everything when you only need to search across a subset of media. Skips files whose visual data is already in memory.
- [Load transcription data into memory](https://docs.getjumper.io/api-reference/analysis-data/load-transcription-data-into-memory.md): Loads all transcription data from the analysis folder into memory. This enables the `/search/transcript` endpoint. Transcription data is also loaded automatically when using `/analysis-data/load`. Does not require a specific whisper model to be loaded — transcriptions from any supported model are lo…
- [Get metadata filter facets](https://docs.getjumper.io/api-reference/metadata-filters/get-metadata-filter-facets.md): Returns curated metadata filter facets and coverage for a searchable scope. Call this before search to render available filter options, then pass selected filters to visual or transcript search using `metadata_filter_request`.
- [Search by text query](https://docs.getjumper.io/api-reference/search/search-by-text-query.md): Semantic visual search — finds moments in analyzed media that match a natural-language description. Analysis data must be loaded into memory first. Results are ordered best-first, but Jumper does not return similarity scores.
- [Search by reference image](https://docs.getjumper.io/api-reference/search/search-by-reference-image.md): Finds moments visually similar to a reference image. Optionally combine with a text query to refine results. Results are ordered best-first.
- [Search by video frame](https://docs.getjumper.io/api-reference/search/search-by-video-frame.md): Extracts a frame at the given timestamp from a video, then finds visually similar moments across all loaded media. Useful for "find more like this" features. Results are ordered best-first.
- [Search transcriptions by text](https://docs.getjumper.io/api-reference/search/search-transcriptions-by-text.md): Searches through loaded speech transcriptions for segments containing the query string. Uses case-insensitive substring matching. Transcriptions must be loaded into memory first (via `/analysis-data/load` or `/analysis-data/load-transcriptions`). Optionally filter to transcript segments assigned to…
- [Get transcriptions](https://docs.getjumper.io/api-reference/transcriptions/get-transcriptions.md): Returns cached speech transcriptions for the given media files. Files must have been transcribed via the `/analyze` endpoint first.
- [Get a bounded transcript range](https://docs.getjumper.io/api-reference/transcriptions/get-a-bounded-transcript-range.md): Returns transcript segments that overlap one half-open source range (`segment_start < end_seconds` and `segment_end > start_seconds`). Pass `hash_str` to avoid reading the source media path. Responses are bounded; when `truncated` is true, repeat the same range with the returned `next_after_segment_…
- [Get thumbnails at specific timestamps](https://docs.getjumper.io/api-reference/thumbnails/get-thumbnails-at-specific-timestamps.md): Returns base64-encoded JPEG thumbnails for the requested media/timestamp pairs.
- [Get thumbnails for a time range](https://docs.getjumper.io/api-reference/thumbnails/get-thumbnails-for-a-time-range.md): Returns a series of thumbnails spanning a time range in a video. Useful for building timeline scrubbers or scene overview strips.
- [List face clustering jobs](https://docs.getjumper.io/api-reference/face-clustering/list-face-clustering-jobs.md): Returns all clustering jobs and summary statistics for each.
- [Get sample face images per cluster](https://docs.getjumper.io/api-reference/face-clustering/get-sample-face-images-per-cluster.md): Returns a few sample face thumbnail images for each cluster in a job. Useful for building a "who is this person?" UI.
- [Get paginated cluster faces](https://docs.getjumper.io/api-reference/face-clustering/get-paginated-cluster-faces.md): Returns face images for specific cluster(s) with pagination support.
- [Rename clusters](https://docs.getjumper.io/api-reference/face-clustering/rename-clusters.md): Assign human-readable names to clusters (e.g. "John", "Sarah").
- [Re-run face clustering](https://docs.getjumper.io/api-reference/face-clustering/re-run-face-clustering.md): Re-runs clustering on existing face detections with new parameters. Runs asynchronously — returns a task_id for progress tracking.
- [Merge or move faces between clusters](https://docs.getjumper.io/api-reference/face-clustering/merge-or-move-faces-between-clusters.md): Merge entire clusters together, or move individual faces between clusters. Useful for correcting clustering mistakes.
- [List watch folders](https://docs.getjumper.io/api-reference/watch-folders/list-watch-folders.md): Returns all configured watch folders and the background service status.
- [Create a watch folder](https://docs.getjumper.io/api-reference/watch-folders/create-a-watch-folder.md): Adds a new folder to be automatically analyzed when new media files appear. The folder must exist on disk. Exclusion glob patterns are matched against the filename only, not the full path.
- [Update a watch folder](https://docs.getjumper.io/api-reference/watch-folders/update-a-watch-folder.md): Modify settings for an existing watch folder. Only include fields you want to change. Filename exclusion glob patterns are matched against the filename only, not the full path. Folder exclusion glob patterns without slashes match folder names; patterns with slashes match relative folder paths segmen…
- [Delete a watch folder](https://docs.getjumper.io/api-reference/watch-folders/delete-a-watch-folder.md): Removes a watch folder from the configuration. Does not delete analysis data.
- [Start the watch folder service](https://docs.getjumper.io/api-reference/watch-folders/start-the-watch-folder-service.md): Starts the background service that monitors watch folders for new media. The service uses the enabled watch-folder configuration already persisted in settings.
- [Stop the watch folder service](https://docs.getjumper.io/api-reference/watch-folders/stop-the-watch-folder-service.md): Stops the background watch folder monitoring service.
- [Get watch folder service status](https://docs.getjumper.io/api-reference/watch-folders/get-watch-folder-service-status.md): Returns whether the background service is running and its current state.
- [Get cache folder paths for a media file](https://docs.getjumper.io/api-reference/utilities/get-cache-folder-paths-for-a-media-file.md): Returns the visual and audio cache folder paths for a specific media file. Useful for inspecting or managing analysis data on disk.
- [Export trimmed video clips](https://docs.getjumper.io/api-reference/export/export-trimmed-video-clips.md): Exports trimmed video clips to a folder using ffmpeg. Each clip specifies a source file and in/out points. Supports subfolder organization.
- [Generate Premiere Pro XML sequence](https://docs.getjumper.io/api-reference/export/generate-premiere-pro-xml-sequence.md): Generates a Premiere Pro compatible XML sequence file (XMEML v4) from a list of clips. The XML can be imported into Premiere Pro, DaVinci Resolve, Avid, or other NLEs.
- [Export transcript to file](https://docs.getjumper.io/api-reference/export/export-transcript-to-file.md): Export transcript segments to a file in TXT, CSV, DOCX, or PDF format. If output_path is omitted, saves to ~/Desktop/{display_name}.{format}.

## OpenAPI Specs

- [openapi-v1](/api-reference/openapi-v1.yaml)
- [openapi](/api-reference/openapi.json)
- [openapi-v1](/developers/openapi-v1.yaml)

## Optional

- [Buy Jumper](https://getjumper.io/#pricing)
- [Discord Community](https://discord.getjumper.io/)
- [YouTube](https://www.youtube.com/channel/UCPaAO35CauOy3XOOUSZoSEw)
- [Blog](https://getjumper.io/blog)