Communitygithub.com

NousResearch/whisper

Name: NousResearch/whisper
Author: Community

Transcribe and translate speech in 99 languages.

What is whisper?

whisper is a Claude Code agent skill that transcribe and translate speech in 99 languages.

Works with~Claude Code~Codex CLI~Cursor

npx skills add https://github.com/NousResearch/hermes-agent/tree/main/optional-skills/mlops/whisper

Open a new chat with this agent skill pre-loaded.

Transcribe and translate speech in 99 languages.

This repo contains 6 individual skills — each has its own dedicated page.

ASCII video: convert video/audio to colored ASCII MP4/GIF.

Generate images, video, and audio via diffusion workflows.

Render MP4/WebM videos from HTML compositions.

Run 150+ AI apps (image, video, LLM) via inference.sh CLI.

Plan and run multi-agent video production pipelines.

Manim CE animations: 3Blue1Brown math/algo videos.

Extract frames or short clips from videos using ffmpeg.

Summarize or transcribe URLs, YouTube/videos, podcasts, articles, transcripts, PDFs, and local files.

Agent skill 'nextjs-turbopack' from affaan-m/everything-claude-code.

Agent skill 'carrier-relationship-management' from affaan-m/everything-claude-code.

Agent skill 'manim-video' from affaan-m/everything-claude-code.

Agent skill 'motion-advanced' from affaan-m/everything-claude-code.