transcript-speechify

Transform transcripts into topic-organized speech documents with planning artifacts.

2|Updated Apr 7, 2026
One-click install
npx skills add https://github.com/soumyaray/ray-ai-skills --skill transcript-speechify
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: transcript-speechify
Source: https://github.com/soumyaray/ray-ai-skills/tree/main/ray-transcript-speechify
Command: npx skills add https://github.com/soumyaray/ray-ai-skills --skill transcript-speechify

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Transform a raw transcript into a clean, flowing speech document organized by topical sections (not slide-by-slide or timestamp-by-timestamp), preserving the speaker's natural voice while removing live-delivery artifacts.

Core Features & Use Cases

  • Analyze the transcript to identify structure, tone, and content categories.
  • Build a topic-centric outline and convert sections into a coherent narrative with logical transitions.
  • Generate a PLAN.speechify.md and calibration notes to guide planning, transformation, and assembly.
  • Trigger on phrases like "speechify" or "polish this talk" to start the transformation.

Quick Start

Use /transcript-speechify <path-to-transcript>.

Frequently Asked Questions about transcript-speechify

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert a raw transcript into a polished speech document?

To convert a transcript into a polished speech, use a transformation process that analyzes structure, builds a topic-centric outline, and removes live-delivery artifacts. This restructures content by topical sections rather than chronological timestamps to create a coherent narrative.

Can I reorganize podcast transcripts by topic instead of chronological order?

Yes, you can reorganize podcast transcripts by topic instead of chronological order. The process analyzes content categories and restructures sections topically, applying logical transitions to convert fragmented spoken dialogue into a flowing, coherent narrative document.

How do I remove live-delivery artifacts from lecture transcripts?

Removing live-delivery artifacts from lecture transcripts involves analyzing the text to identify spoken filler and structural disorganization. The content is then restructured into a clean, topic-centric outline that preserves the speaker's natural voice while eliminating distracting delivery elements.

What is the best way to outline a talk transcript for a coherent narrative?

The best way to outline a talk transcript for a coherent narrative is to generate a topic-centric plan. This approach identifies core content categories, reorganizes sections by topic rather than slide order, and applies logical transitions between sections.

Does this transcript transformation process work with varying transcript structures?

Yes, the transcript transformation process works with varying transcript structures. It analyzes the specific structure of the input transcript and handles varying formats to produce a unified, topic-centric speech document with calibration notes.

Do I need calibration notes and a planning artifact to polish a transcript?

Yes, generating a planning artifact and calibration notes is part of the process to polish a transcript. These elements guide the planning, transformation, and assembly phases to ensure the final speech document maintains a coherent narrative and natural voice.