Video creation glossary
Clear definitions for 100 terms across AI video generation, social media video, captions, formats, and production workflows.
- 100 terms
- 6 categories
Browse by category
Video Editing
15 terms
- Video ClippingVideo clipping is the process of extracting short, high-value segments from longer video content for distribution as standalone clips on social media platforms.
- Video ReframingVideo reframing is the process of changing a video's aspect ratio by intelligently cropping or repositioning the frame, typically to convert horizontal 16:9 footage into vertical 9:16 for short-form platforms.
- Jump CutA jump cut is an abrupt edit that cuts between two shots of the same subject from nearly identical camera angles, creating a jarring visual discontinuity or rapid time compression effect.
- KeyframeA keyframe is a defined point in a video timeline that specifies the value of an animation parameter (position, scale, opacity, color) at that moment, with the software interpolating values between keyframes.
- TimelineA video timeline is the linear, time-based interface in a video editor where clips, audio tracks, graphics, and effects are arranged in sequence to compose the final video.
- Split ScreenSplit screen is a video editing technique that divides the frame into two or more sections, each showing different footage simultaneously.
- TransitionA transition is a visual effect applied between two video clips or scenes to create a smooth or stylized changeover from one to the next.
- Video StabilizationVideo stabilization is a technique that reduces unwanted camera shake and jitter in footage, producing smoother motion through hardware gimbal systems or software post-processing.
- CropCropping is the process of removing portions of a video or image frame to change its composition, aspect ratio, or to focus on a specific area of the content.
- TrimTrimming is the process of shortening a video by removing content from the beginning, end, or both, without affecting the middle portion of the clip.
- Silence RemovalSilence removal is an automated editing technique that detects and removes silent or low-audio segments from video, tightening pacing and improving viewer retention.
- Video OverlayA video overlay is any visual element layered on top of the primary video footage, including text, logos, lower thirds, graphics, stickers, or other decorative elements.
- Video MontageA video montage is an editing technique that combines multiple short clips into a sequence to convey the passage of time, compress a process, or build an emotional narrative.
- UpscalingVideo upscaling is the process of increasing a video's resolution beyond its original capture resolution using interpolation or AI super-resolution models.
- LUTA LUT (Look-Up Table) is a preset color transformation file that maps input color values to output values, used to apply consistent color grades across video footage.
AI Video Generation
14 terms
- Faceless VideoA faceless video is a video in which the creator does not appear on camera. It can use screen recordings, product footage, slides, animation, stock clips, or AI visuals. Narration, on-screen text, and captions carry the message; AI and a voiceover are optional.
- AI Video GenerationAI video generation is the process of creating video content from text prompts, images, or other inputs using artificial intelligence models that generate visual frames, motion, and scene composition.
- Text-to-VideoText-to-video is an AI capability that converts written text descriptions into video clips, generating visuals, motion, and scene composition from natural language prompts.
- Prompt-to-VideoPrompt-to-video is a workflow where a user provides a text prompt, topic, or script, and the system automatically generates a complete video including visuals, voiceover, captions, and editing.
- Text-to-SpeechText-to-speech (TTS) is AI technology that converts written text into spoken audio, generating natural-sounding human voices from text input for use as voiceover in video and audio production.
- AI ModelAn AI model is a machine learning system trained on large datasets to perform a specific task, such as generating video from text, transcribing audio, synthesizing speech, or analyzing content.
- Fine-TuningFine-tuning is the process of further training a pre-trained AI model on a smaller, specialized dataset to adapt its outputs to a specific style, domain, subject, or voice.
- Highlight DetectionHighlight detection is an AI capability that analyzes long-form video or audio content and automatically identifies the most engaging, notable, or share-worthy moments for use as standalone clips.
- Image-to-VideoImage-to-video is an AI capability that animates a static image into a video clip, adding motion, camera movement, and scene dynamics based on the source image and optional text guidance.
- Lip SyncLip sync in video production is the synchronization of a character's or person's lip movements with an audio track, either naturally filmed or generated by AI.
- AI AvatarAn AI avatar is a computer-generated virtual presenter or character that can deliver scripted speech with realistic facial expressions, lip sync, and body language.
- Prompt EngineeringPrompt engineering is the practice of crafting effective text instructions for AI models to generate desired outputs, whether images, videos, text, or other content.
- AI B-RollAI B-roll is supplementary video footage generated by artificial intelligence to visually illustrate narration, replacing the need for traditional stock footage or filming.
- AI Image GenerationAI image generation is the process of creating images from text descriptions using AI models like FLUX, Stable Diffusion, Midjourney, or DALL-E that produce visual content from natural language prompts.
Social Media Video
16 terms
- Short-Form VideoShort-form video is video content typically under 60 seconds, optimized for vertical mobile viewing on platforms like TikTok, YouTube Shorts, and Instagram Reels.
- HookA hook is the opening 1-3 seconds of a short-form video, designed to immediately capture viewer attention and prevent scrolling past the content.
- CTA OverlayA CTA overlay (call-to-action overlay) is a graphic element displayed on top of a video that prompts viewers to take a specific action, such as subscribing, clicking a link, or following an account.
- AudiogramAn audiogram is a video format that visualizes audio content as a static or animated image with a waveform visualization, used to share podcast clips, music, or spoken word content on social media platforms that require video.
- YouTube ShortsYouTube Shorts is YouTube's short-form vertical video format for videos up to 60 seconds long, displayed in a dedicated Shorts feed and distributed by YouTube's recommendation algorithm to non-subscribers.
- Instagram ReelsInstagram Reels is Instagram's short-form vertical video format for videos up to 90 seconds, distributed through a dedicated Reels feed and Instagram's Explore page to reach audiences beyond existing followers.
- TikTokTikTok is a short-form video platform owned by ByteDance that distributes videos primarily through an algorithm-driven feed (For You Page) based on content performance rather than the creator's follower count.
- Social Media AlgorithmA social media algorithm is a set of rules and machine learning models that platforms use to rank, recommend, and distribute content to users based on engagement signals.
- Watch TimeWatch time is the total amount of time viewers spend watching a video, measured as both absolute duration and as a percentage of the video's total length (retention rate).
- Engagement RateEngagement rate is the percentage of viewers who interact with a video through likes, comments, shares, saves, or other actions relative to the total number of views or followers.
- Content CalendarA content calendar is a planning tool that schedules what content to publish, on which platforms, and when, helping creators maintain consistent posting frequency.
- Video AnalyticsVideo analytics are metrics and data insights about how viewers interact with video content, including views, watch time, retention curves, engagement rate, and audience demographics.
- Multi-Platform PublishingMulti-platform publishing is the strategy of distributing the same or adapted video content across multiple social platforms simultaneously to maximize reach and audience growth.
- Video RepurposingVideo repurposing is the process of transforming existing video content into new formats, lengths, or styles to extend its value across multiple platforms and audiences.
- A/B TestingA/B testing for video is the practice of publishing two or more variations of a video element (thumbnail, hook, caption style, CTA) to determine which performs better with real audience data.
- Video SEOVideo SEO is the practice of optimizing video content for discovery in search engines, platform search, and AI-powered search results through metadata, transcripts, and structured data.
Captions & Subtitles
9 terms
- AI CaptionsAI captions are automatically generated text overlays synchronized to spoken audio in a video, created using speech recognition AI that transcribes audio and places text with word-level timing.
- Caption StylesCaption styles are visual design presets that control how text captions appear on screen, including font, color, size, position, background, and animation effects.
- Word-Level SyncWord-level sync is a captioning precision where each individual word is timed to appear or animate at the exact moment it is spoken in the audio, rather than showing full sentences at once.
- SRT SubtitlesSRT (SubRip Text) is a plain-text subtitle file format that stores timed text with sequence numbers, timestamps, and subtitle content for displaying text over video.
- TranscriptionTranscription is the process of converting spoken audio from a video or audio recording into written text, producing a verbatim or edited text document representing the spoken content.
- Auto CaptionAuto captioning is the process of automatically generating text captions from spoken audio in a video using AI speech recognition, without manual transcription.
- Burned-In CaptionsBurned-in captions (also called hardcoded or open captions) are text overlays permanently embedded into the video pixels, visible to all viewers without toggles.
- Closed CaptionsClosed captions are text overlays stored as a separate data track alongside the video, allowing viewers to toggle them on or off in their player settings.
- Video AccessibilityVideo accessibility refers to making video content usable by people with disabilities, including captions for deaf viewers, audio descriptions for blind viewers, and navigable player controls.
Video Formats & Codecs
20 terms
- Vertical VideoVertical video is video that is taller than it is wide. A common format is 9:16, such as 1080 pixels wide by 1920 pixels high, for portrait viewing on a phone. Other portrait ratios, including 4:5, are also vertical; the aspect ratio describes shape, not duration.
- Aspect RatioAspect ratio is the proportional relationship between a video's width and height, expressed as two numbers separated by a colon (e.g., 16:9 for landscape, 9:16 for vertical, 1:1 for square).
- Video CompressionVideo compression is the process of reducing video file size by removing redundant visual data using codecs, while maintaining acceptable visual quality for the intended use.
- CodecA codec is a software algorithm that encodes raw video data into a compressed format for storage or transmission, and decodes it for playback. Common video codecs include H.264, H.265 (HEVC), VP9, and AV1.
- BitrateBitrate is the amount of data used to represent each second of video, measured in kilobits per second (Kbps) or megabits per second (Mbps). Higher bitrate generally produces better video quality at the cost of larger file size.
- Safe ZoneA video safe zone is the area where you aim to keep faces, captions and important details clear of app controls, descriptions and cropping. Its size changes with the platform, placement and device.
- Export PresetAn export preset is a saved configuration of video output settings including codec, resolution, bitrate, aspect ratio, and format, allowing creators to apply consistent export parameters across multiple projects.
- ResolutionVideo resolution is the number of pixels displayed in each frame, expressed as width by height (e.g., 1920x1080 for 1080p, 3840x2160 for 4K), determining the sharpness and detail level of the video.
- Frame RateFrame rate is the number of individual video frames displayed per second (fps), determining the smoothness and motion character of video playback. Common frame rates are 24fps (cinematic), 30fps (broadcast), and 60fps (smooth action).
- EncodingVideo encoding is the process of converting raw or uncompressed video data into a compressed digital format using a codec, producing a file suitable for storage, streaming, or distribution.
- StreamingVideo streaming is the delivery of video content over the internet in real time, where the video is played as data arrives rather than requiring a complete file download before playback begins.
- 16:9 Aspect Ratio16:9 is the standard widescreen aspect ratio used for YouTube videos, TV broadcasts, and most desktop displays, measuring 16 units wide by 9 units tall.
- 9:16 Aspect Ratio9:16 is the vertical video aspect ratio used for TikTok, Instagram Reels, YouTube Shorts, and Snapchat, measuring 9 units wide by 16 units tall.
- LetterboxingLetterboxing is the practice of adding black or colored bars above and below a video to display widescreen content within a different aspect ratio frame.
- Video FormatA video format is a file container specification that defines how video, audio, metadata, and subtitle tracks are packaged together, such as MP4, MKV, MOV, or WebM.
- H.264H.264 (also called AVC) is the most widely used video compression codec, delivering good quality at relatively low bitrates with near-universal device and platform compatibility.
- H.265H.265 (also called HEVC) is a video compression codec that delivers up to 50% better compression than H.264 at the same quality, enabling smaller files and higher resolutions.
- GIFGIF (Graphics Interchange Format) is an image format that supports short looping animations without audio, commonly used for memes, reactions, and social media previews.
- 1:1 Aspect Ratio1:1 is a square aspect ratio used primarily for Instagram feed posts, Facebook posts, and social media ads, measuring equal width and height.
- 4K Video4K video is a resolution standard of approximately 4000 horizontal pixels, most commonly 3840x2160 (4K UHD), offering four times the detail of standard 1080p Full HD.
Video Production
26 terms
- B-RollB-roll is supplementary footage used to visually support the main narrative of a video, providing visual variety while voiceover or dialogue continues over the cut.
- Workflow AutomationIn video production, workflow automation is the use of templates, presets, and AI to automate repetitive steps in the video creation pipeline, from script to export.
- Content RepurposingContent repurposing is the strategy of adapting a single piece of content into multiple formats and platforms to maximize reach and ROI from one production effort.
- Stock FootageStock footage is pre-recorded video clips licensed for use in new productions, covering a wide range of subjects, locations, and scenarios without requiring original filming.
- Motion GraphicsMotion graphics are animated graphic design elements used in video, including moving text, logos, icons, transitions, lower thirds, charts, and callouts that explain or emphasize information on screen.
- Color GradingColor grading is the process of adjusting the colors, contrast, saturation, and tonal balance of video footage to achieve a consistent visual style or enhance the mood of the content.
- RenderRendering is the process of processing a video timeline or composition into a final output video file, combining all clips, effects, transitions, audio, and graphics into a single exportable format.
- StoryboardA storyboard is a visual planning document showing a sequence of illustrated or described scenes depicting the planned shots, camera angles, and composition of a video before production begins.
- SceneIn video production, a scene is a single continuous shot or logically grouped segment within a video, representing one unit of visual content covering a specific moment, location, or idea.
- VoiceoverA voiceover is narration or dialogue recorded separately from on-screen visuals and laid over the video during editing, providing audio context without showing the speaker on camera.
- Batch ProcessingBatch processing in video production is the simultaneous or sequential automated processing of multiple videos or tasks, applying the same operations to a group of files without manual intervention between each.
- WatermarkA watermark is a semi-transparent or opaque overlay embedded in a video that identifies the content's source, brand, or creator, typically as a logo, text, or combined mark.
- Green ScreenA green screen is a solid green backdrop used during filming that is replaced with another image or video in post-production using chroma key compositing technology.
- Chroma KeyChroma key is a post-production compositing technique that removes a specific color (typically green or blue) from a video layer and replaces it with another image or video, enabling subjects to appear in virtual environments.
- ThumbnailA thumbnail is a small preview image that represents a video, displayed on platforms like YouTube, TikTok, and Instagram before a viewer clicks to watch.
- Royalty-FreeRoyalty-free refers to media (music, images, video footage) that can be used after a one-time license purchase without paying recurring royalties per use or per view.
- Video APIA video API is a programmatic interface that allows developers to integrate video processing, editing, transcription, or generation capabilities into their applications.
- WebhookA webhook is an HTTP callback that sends a notification to a specified URL when an event occurs, enabling real-time communication between services without polling.
- Background MusicBackground music is audio played underneath the primary content of a video (narration, dialogue, or ambient sound) to set mood, pace, and emotional tone.
- DubbingDubbing is the process of replacing or adding a new audio track in a different language over existing video footage, enabling multilingual content distribution.
- Video TemplateA video template is a pre-designed layout with placeholder content that creators customize with their own media, text, and branding to produce videos quickly.
- Render QueueA render queue is a list of video export jobs waiting to be processed sequentially or in parallel, enabling batch export of multiple videos without manual intervention.
- Video SDKA video SDK (Software Development Kit) is a packaged set of libraries, tools, and documentation that developers use to integrate video capabilities into their applications.
- Noise ReductionNoise reduction is the process of removing unwanted background noise from video audio tracks, improving clarity and professionalism of spoken content.
- Video PodcastA video podcast is a podcast episode recorded with video cameras in addition to audio, distributed as both audio-only and video content across podcast and video platforms.
- Cloud RenderingCloud rendering is the process of exporting and processing video on remote servers with GPU acceleration instead of using local computer hardware.
Create
Create your next short-form video now.
Start with one raw clip or a long-form recording. BlitzReels gives you the captions, clipping, cleanup, and export tools in one place.
Create my first short7-day trial includedFull workflow testSingle clips and clipping
New short-form project
Drop video or paste a URL
Upload source video
Clip, caption, reframe, clean up, export
ClipReframeCaptionExport