agentino

Fully generative: script → LLM storyboard → AI images + TTS → captioned MP4. Flagship video pipeline.

Text → narrated WAV + SRT. edge-tts / say / piper. Pure local, cross-platform.

Images + optional audio → MP4 slideshow with Ken Burns zoom and xfade transitions. Pure ffmpeg.

Add YouTube / QuickTime chapter markers to an MP4 via ffmetadata — no re-encode, just metadata.

One-shot: analyse a video, then cut its silence gaps. Chains video-brief + video-cut-silences. Pure ffmpeg.

Text → PNG via OpenAI Images (gpt-image-1/dall-e-3) or OpenRouter multimodal chat (Gemini Flash Image, Flux, ...).

Narration script → N-shot storyboard: LLM plans shots, image model renders. Feeds video-slideshow.

Concatenate N video clips into one MP4, normalising resolution/fps, with optional crossfade.

Overlay timed text bands (lower-thirds, chapter markers, call-outs) on a video. One ffmpeg pass.

An LLM workspace that watches LLM inference — what launched, what it costs, how fast it runs, and who serves it. Four agents on live OpenRouter and Artificial Analysis data. Built on Runspace + Agentino.

LLM-readable video brief — metadata + silence gaps + scene changes + thumbnails. Pure ffmpeg, no cloud.

Picture-in-picture composition: overlay an inset video on a main video with configurable position, scale, border.

Burn SRT/VTT subtitles into the video stream with full styling control. ffmpeg-only.

Agentino marketplace registry (provisional) — index.json of 14+ publicly-installable skills

Prepend branded intros and append outros to a video with smooth crossfades. Auto-normalises mismatched formats.

One-shot: script + images → captioned narrated MP4. Chains voiceover + slideshow + captions. Pure local.

Speed up or slow down a video (0.25x-4x) with pitch-preserving atempo chain for natural voice.

Mix a music bed under a video with automatic sidechain ducking. ffmpeg-only, no cloud.

Remove silences from a video with inaudible crossfades. ffmpeg-only, no cloud.