Showing all 6
Speech
6 records filed under this subject, newest first, each with what it is, what it cost and where the builder got stuck.
Records
6
139anything2explainerA skill for Claude Code and Codex that turns a topic, or a document, into a 1280×720 narrated explainer film, with every frame drawn in code rather than generated and each agent in the parallel build writing one Remotion component. The same author’s video-shotcraft makes product promos out of 157 shot cards and a sound-design pass; this one is driven by the narration, ships no sound effects or music, and freezes the words into frame numbers before any shot is built.ClaudeClaude CodeCodex
123video-talkcraftAn agent skill that turns Claude Code or Codex into a motion-design studio for narration videos: hand it a script and a finished voice track and it aligns the two word by word on your own machine, storyboards every semantic beat, then renders the film from 108 motion recipe cards under a camera system defined by subtraction. Where video-shotcraft makes product promos out of 157 shot cards and a sound-design pass, and anything2explainer turns a topic into an explainer whose narration becomes frame numbers, this one takes a voice track that already exists and treats it as the clock.ClaudeClaude CodeCodex+2
096Skill RecorderA macOS-first Electron desktop app that records a real work session (screen video, app and window switches, browser URLs, clipboard previews, an optional session-owned terminal and spoken narration) then hands the timeline to the bundled GitHub Copilot CLI, which reconstructs one overall intent plus an ordered list of steps and turns the approved version into a SKILL.md procedure or a scheduled automation for Microsoft Scout, Microsoft 365 Copilot Cowork or Copilot Studio.GitHub CopilotWhisper
067VibeRaveA fork of Strudel that lets you hold a key, say a genre out loud, and have the music change on the next bar without the beat ever stopping.Claude
020Moonshine VoiceA speech stack for voice agents and interfaces: transcription, intent recognition and text to speech, built to run at low latency on small devices, with 74 of its recent commits co-authored by Cursor.Claude
001whisper.cppOpenAI’s Whisper speech recognition rewritten in C/C++, so it runs on a CPU, a phone, or in a browser tab.Whisper




