
Clips listos de tu podcast, live o programa de entrevistas, pensados para el español. Si dos personas están lado a lado, quedan una arriba de la otra con el subtítulo en la franja del medio. Subtítulos palabra por palabra con tildes y signos correctos (ñ, ¿, ¡) y opción de ocultar groserías. Cada clip trae título, descripción, hashtags y la línea "Episodio completo". De 5 a 8 MP4 9:16 por pedido.

Open-source CLI (MIT, 2k+ GitHub stars, Hacker News front page). Turn any video URL or local file into scene-aware keyframes plus a timestamped, speaker-labeled transcript your LLM can actually read. - Runs 100% on your machine, nothing is uploaded - Works with Claude, ChatGPT, Gemini or local models - URL videos reuse the platform's own captions, Whisper otherwise New in 0.10.5: Apple Silicon GPU transcription, about 6x faster on M-series Macs, same no-fake-captions gate.

Upload a long talking video and get up to three captioned short clips, right in your browser. No install, no API key. Chinese (Traditional, Taiwan) or English captions, vertical 9:16 with black bars or keep landscape, MP4 + SRT for every clip, and fix any caption just by chatting. Up to 500 MB / 20 minutes.

Download package that runs on your own computer inside your AI agent (e.g. Claude Code or Codex — that agent's subscription/API costs are yours). Requires Python 3.9+, ffmpeg and faster-whisper (free; 150–500 MB model download on first run). You supply the footage: it transcribes locally, your agent picks self-contained moments, and the scripts cut 9:16 clips with word-timed captions, a hook banner, titles and hashtags. No other third-party services or keys.

Pega un enlace a tu pódcast, entrevista, directo o charla, o sube el video, y recibe clips verticales terminados: los momentos que se entienden solos, cortados a 9:16, con subtítulos palabra por palabra, encuadre que sigue a quien habla, sonido nivelado, y título, frase de apertura y texto para publicar. Enlace de Google Drive o Dropbox: los MP4. Enlace de YouTube: primero el plan de clips.

Give an idea or your draft, a length (15 s to 15 min) and a platform. CueCard writes or tightens a spoken script that fits the length, times every word from syllables, pauses and your pace, and returns a teleprompter PDF (normal and mirrored), SRT and VTT captions timed before you record, a shot list with B-roll and on-screen text, and a script check: hook, sentence length, readability, required words.

Upload a long podcast, lecture or interview and get up to 5 vertical 1080x1920 shorts back in the chat. ShortLoom picks segments by loudness, speech and motion, trims pauses, reframes to 9:16 by following faces, and burns in word-timed captions. Or name the moments yourself, like "3:10 to 3:50". Runs in the Capafy cloud, nothing to install. Measured: a 9:40 video became 5 captioned shorts in 62 s on 2 CPUs. It does not judge jokes or story beats.

Turn one video transcript into 10 short-form content ideas, powerful hooks, engaging captions, platform-ready titles, hashtags, and a 30-day content calendar. Supports English, Urdu, and Hindi transcripts. Text-based content planning only; video rendering and editing are not included.

A Claude Code skill + Remotion project for narrated videos where voice, word-by-word captions and UI motion land together. ElevenLabs timing so captions never drift, keyword slams, beat-snapped cuts, one spec to 9:16 / 16:9 / 1:1, 6 themes or one brand hex, and self-QA (frozen frames, -14 LUFS). You write the script; Claude builds, renders and checks the MP4. Needs Node 18+, FFmpeg and your own ElevenLabs key.