Captions & subtitles models & tools for AI video

For AI agents: find the right skill in one call — curl -s "https://skills.varg.ai/api/search?q=<what the person wants>" returns the matching use case and the best skills with install commands, as markdown (Russian works too). Full index: https://skills.varg.ai/llms.txt. Every page has a markdown twin: add .md to its path. Before generating anything, show the person the options on the use-case page.

3 models & tools for captions & subtitles: animated and word-by-word captions, subtitles, transcription and translation.

Models & tools (3)

• ElevenLabs Speech to Text — ElevenLabs: Transcribe audio and video with word timestamps, speaker labels and keyterms, ready for subtitles.
• ElevenLabs Speech to Text (inference.sh) — inference.sh: Transcribe audio with ElevenLabs Scribe, speaker diarization and forced alignment, via inference.sh.
• Speech to Text — inference.sh: Transcribe audio with ElevenLabs Scribe v2 or Whisper V3 Large, with timestamps and speaker labels.

More for captions & subtitles

Effects (5)

• 3D Camera Captions — HeyGen: Captions that live in 3D around a talking head: the camera flies through the words, heroes pass behind the speaker.
• Remotion Captions — Remotion: Transcribe speech and burn in animated captions with Remotion, or import an existing SRT file.
• Cinematic Caption — Audrey, beta: Designed editorial captions for HyperFrames: scored hero words, subject-aware depth, glass type — not a subtitle strip.
• Caption Animation — iart.ai: Word-timed TikTok captions in Remotion or CSS: per-word pop, active-word highlight, 9:16 safe areas, sidecar SRT/VTT.
• Agent Caption — Ali Hamza Kamboh, beta: Local captions in any language: Whisper words, forced-aligned timing, SRT/VTT, burned styles or a GSAP captions.js.

Guides (6)

• Pretext Text Metrics — Yaniv Golan, beta: Measure and fit text without the DOM using pretext: auto-fit sizes, know line breaks before render, canvas/WebGL text.
• Chinese Font Selector — Songzhi-lab, beta: Pick Chinese fonts by license tier first (OFL, vendor-free, avoid), then by scene and mood, with Latin pairings.
• Transcribe Anything — Shawn Wang (swyx): Transcribe hours of audio or video with whisper, whisperX or cloud STT: word timestamps, speaker labels, SRT/VTT.
• FFmpeg Captions and Subtitles — Josiah Siegel: FFmpeg subtitle reference: burn SRT/ASS/VTT with libass, soft tracks, conversion, styling and FFmpeg 8's Whisper filter.
• Subtitle Translator — Matheus Castro: Agent-translated SRT/ASS subtitles in resumable batches that keep cue count, timing and ASS styling tags intact.
• WJS Translating Subtitles — Jian Shuo Wang: Translate an SRT to Chinese, English or another language and re-cut cues at real punctuation; bilingual SRTs too.

Other kinds of skills

• Prompts: The words a video model obeys: camera angles, shot sizes, lighting, characters, hooks and prompt guides for Seedance, Kling, Veo, FLUX and Higgsfield. Your agent writes the prompt with them, or you paste them into the model.
• Effects: An effect you can see, added to your video: animated titles, captions, transitions, shader backgrounds, logo animations, device mockups and viral camera tricks. Hand your agent the footage or the brief and get the effect.
• Styles: The look of the whole video: art styles, film looks, color grades and LUTs, caption fonts and style references. Pick a style and every shot your agent makes follows it.
• Guides: Know-how your agent reads before it works: how to write a script, storyboard, edit and caption, and how to use Remotion, HyperFrames, GSAP, Three.js and FFmpeg.
• Workflows: A brief in, a finished video out: UGC ads, product videos, music videos, talking heads, explainers, Shorts and short dramas, step by step, with the models and the edit chosen for you.