pulse / docs /feature-map.md
vikasbanjare's picture
Pulse by aifloh
78bfc3e
|
Raw History Blame Contribute Delete
4.73 kB

A newer version of the Gradio SDK is available: 6.32.0

Upgrade

Feature map: Captions.ai, Kapwing, VEED β†’ Pulse

Scraped 2026-10-17 from the public tool indexes (captions.ai, kapwing.com/tools, veed.io/tools). Kapwing lists 342 tool pages, VEED 1,161 (most are SEO variants of the same tool). Grouped below by capability, with how Pulse implements each for free, locally, with no API keys.

Capability Captions.ai Kapwing VEED Pulse (free/local) Status
Auto captions, word timestamps βœ” 100+ styles βœ” subtitles/caption-generator βœ” add-subtitles, animated-subtitles faster-whisper large-v3-turbo (CTranslate2, CPU int8), word timestamps + VAD v1
Caption styles / animations AI Edit styles (152) basic presets basic presets 20 presets derived from the measured Captions.ai patterns (word-fill, blur-pop, append, line-stack, pills, bars, moving highlight box, hollow inactive, emphasis colour/size/glow) v1
Caption editor (text, timing, split/merge) βœ” βœ” subtitles/editor βœ” word list editor, click to delete/emphasise, drag timing on timeline v1
SRT / VTT export & import βœ” βœ” srt/vtt maker, converter βœ” /api/subtitles/srt, drop .srt to import v1
Translate subtitles βœ” 100+ langs βœ” subtitles/translator βœ” argos-translate offline packages (download on demand) v2
Text-based editing (delete words = cut video) βœ” Trim pauses βœ” smart-cut βœ” cuts list + timeline remap; preview skips cuts; export applies v1
Filler-word removal βœ” βœ” smart-cut/filler-words βœ” regex over transcript (um, uh, like, you know…) + one-click delete v1
Silence removal βœ” βœ” audio-editor/silence-remover βœ” gaps between words > threshold β†’ cuts v1
Auto zoom / punch-ins βœ” AI Edit βœ” keyframing βœ” zoom keys at emphasis cards (pattern G: 1.05–1.08 over 250 ms easeOut) v1
B-roll βœ” AI b-roll βœ” βœ” ai-b-roll-generator user-uploaded B-roll clips/images placed on the timeline; no stock API (needs keys) v2
Text / emoji / sticker overlays βœ” βœ” add-text, add-sticker, add-emojis βœ” overlay layer (text, native emoji, images) drawn by the same canvas engine v1
Resize / reframe (9:16, 1:1, 16:9) βœ” βœ” resize βœ” output aspect + crop position in the compositor v1
Trim / split / merge clips βœ” βœ” βœ” timeline cuts; merge = multi-source timeline v1 / v2
Denoise / enhance speech βœ” Denoise βœ” denoise, audio-enhancer βœ” ai-audio-enhancer ffmpeg afftdn / loudnorm / compressor chain v1
Music & SFX βœ” generate βœ” add-audio βœ” user-provided tracks with ducking (sidechain) ; generation needs a model, out of scope v2
Text to speech β€” βœ” 100+ langs βœ” Kokoro-82M ONNX (free, offline, ~330 MB) v2
Voice clone / AI twin βœ” AI twin βœ” βœ” ai-clone needs F5-TTS / XTTS (multi-GB models); exposed as an optional plugin endpoint, off by default v3
Eye-contact correction βœ” βœ” adjust/eye-contact βœ” no free local model of acceptable quality; not planned β€”
AI avatars βœ” βœ” βœ” out of scope β€”
Background removal / blur β€” βœ” remove-background βœ” ai-background-remover MediaPipe selfie segmentation in browser (free) v3
Screen / webcam recording βœ” βœ” record/* βœ” getUserMedia / getDisplayMedia + MediaRecorder β†’ upload v2
Convert / compress β€” βœ” convert/, compress/ βœ” ffmpeg endpoints v2
Chat / prompt editing βœ” Text to edit βœ” ai/video-assistant βœ” not planned without an LLM key; rule-based "auto edit" button instead β€”
Export βœ” βœ” βœ” client-side WebCodecs (H.264 + AAC via mp4-muxer); server ffmpeg fallback for cuts v1

Captions.ai specifics worth copying

  • Style = font + placement + reveal + entrance + emphasis + box. Every one of the 54 premium styles decomposes into those six fields (see captions-ai-research/caption-motion-patterns.md).
  • Measured defaults: band centre 67 % of height (9:16), 2 words per chunk, chunk hold 0.5 s median, whole-chunk entrance 80–150 ms blur-pop, inactive words 40 %.
  • Four colour slots per basic preset: text, emphasis, stroke/container, glow.

Kapwing specifics

  • Tool index categories: Video Editing, Subtitle/Translate/Transcribe, AI Generators, Audio Tools, Text to Speech, Social Media Editing, Convert & Compress, Image & GIF.
  • "Smart Cut" = silence + filler removal, the same two operations Pulse derives from the transcript.

VEED specifics

  • Same core (subtitles, text-based editing, audio enhance) plus a very long tail of AI image filters; Pulse ignores the image-filter tail.