ai272/speaker

Analysis updated 2026-05-18

★ 94PythonAudience · pm founderComplexity · 2/5Setup · moderate

Mindmap

mindmap
  root((speaker))
    What it does
      Reads full slide content
      Drafts speaker notes
    Pipeline
      Parse pptx structure
      Render slides as images
      OCR embedded text
      Vision review stage
    Outputs
      Display rehearsal notes
      Clean spoken notes
      Vision review packet
    Tech stack
      Python
      OCR
      Claude Code skill
    Audience
      Presenters
      PMs and founders

mindmap root((speaker)) What it does Reads full slide content Drafts speaker notes Pipeline Parse pptx structure Render slides as images OCR embedded text Vision review stage Outputs Display rehearsal notes Clean spoken notes Vision review packet Tech stack Python OCR Claude Code skill Audience Presenters PMs and founders

What do people build with it?

USE CASE 1

Generate rehearsal speaker notes with timing for an existing PowerPoint deck

USE CASE 2

Extract spoken-word notes that get written directly into the PowerPoint notes pane

USE CASE 3

Get an AI reading of chart and screenshot content that plain text extraction would miss

USE CASE 4

Produce a rehearsal document alongside the updated deck for practicing a talk

What is it built with?

PythonOCRClaude Code

How does it compare?

	ai272/speaker	yuzhworkhard-wq/image-to-code	agricidaniel/claude-shorts
Stars	94	94	93
Language	Python	Python	Python
Setup difficulty	moderate	easy	moderate
Complexity	2/5	2/5	3/5
Audience	pm founder	developer	developer

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · moderate Time to first run · 30min

Needs the .claude/skills/ppt-speech-writer skill installed and a vision-capable AI agent.

The README does not state a license.

In plain English

Speaker is a Python-based skill for AI coding assistants (specifically Codex and Claude Code) that generates speaker notes for PowerPoint presentations. Most tools that do this only read the text boxes on each slide, which means they miss charts, screenshots, tables, and labels embedded inside images. This project is built to avoid that gap by looking at slides the way a human would: reading the visible content, not just the raw text layer. The process works in several stages. First it reads the structure of the .pptx file and extracts text boxes, tables, native charts, and any additional XML content that standard libraries miss. Then it renders each slide as an image so that visually complex content, things like SmartArt, grouped shapes, or screenshot overlays, can be inspected. An OCR step reads any text found inside those images, and a vision review stage prepares a summary of each slide's visual elements for a vision-capable AI agent or a human reviewer. From that combined picture of each slide, the skill drafts two sets of notes. One is a display version, meant for rehearsal: it includes slide labels, transitions, pauses, and a timing table. The other is a clean version containing only the spoken words, which gets injected directly into the PowerPoint notes pane. Both are derived from the same grounded source so they stay consistent with each other. The outputs are a new .pptx file with the notes written in, a .docx rehearsal document (with a Markdown fallback if the required library is not installed), and a vision review packet that records the evidence gathered per slide. Intermediate files are saved under a work folder so nothing is lost if a step needs to be rerun. To use it inside Claude Code, the repository provides a project skill at .claude/skills/ppt-speech-writer. After opening Claude Code from the repository root, invoking /ppt-speech-writer starts the full workflow. Before drafting begins, the skill asks the user to confirm the output language, since it does not infer language from the conversation automatically.

Copy-paste prompts

Prompt 1

Run the ppt-speech-writer skill on my deck.pptx and draft speaker notes

Prompt 2

Generate a rehearsal document with pacing notes for this presentation

Prompt 3

Read the charts and screenshots on these slides and summarize what they show

Prompt 4

Write clean spoken-word notes only, no timing labels, for this deck

Frequently asked questions

What is speaker?

A Claude Code and Codex skill that writes PowerPoint speaker notes by actually reading slide visuals, not just the text boxes.

What language is speaker written in?

Mainly Python. The stack also includes Python, OCR, Claude Code.

What license does speaker use?

The README does not state a license.

How hard is speaker to set up?

Setup difficulty is rated moderate, with roughly 30min to a first successful run.

Who is speaker for?

Mainly pm founder.

Open on GitHub → Explain another repo

This repo across BitVibe Labs

Verify against the repo before relying on details.