skills.rest
Sacred-G
Sacred-GCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

transcribe

Transcribe audio files into text with optional speaker diarization using OpenAI models.

2|1|Updated Apr 2, 2026
Search Tags:#automation#cli#transcription#audio#openai#diarization#speech
One-click install
npx skills add https://github.com/Sacred-G/oh-my-claw --skill transcribe-sacred-g
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: transcribe
Source: https://github.com/Sacred-G/oh-my-claw/tree/main/secure-openclaw/skills-main/skills/.curated/transcribe
Command: npx skills add https://github.com/Sacred-G/oh-my-claw --skill transcribe-sacred-g

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires openai, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Transcribing audio and video recordings into text with optional speaker diarization to identify who spoke when, enabling easier search, indexing, and accessibility.

Core Features & Use Cases

  • Audio transcription: Convert speech to text using OpenAI models with deterministic defaults.
  • Diarization and known speakers: Optionally label speakers and provide known speaker references.
  • Workflow automation: Bundle as a CLI tool for repeatable results, output transcripts to output/transcribe paths.
  • Use case: Transcribe interviews, lectures, podcasts with optional speaker mapping.

Quick Start

Run the bundled transcribe_diarize.py CLI on your audio file to obtain a transcript with optional diarization.

Frequently Asked Questions about transcribe

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

FAQPage Schema
How do I transcribe audio files with speaker diarization for interviews or podcasts?▼

Audio transcription with speaker diarization uses OpenAI models to convert speech to text while identifying who spoke when. You can provide known speaker references and language hints to map speakers accurately across interviews, meetings, lectures, and podcasts.

Can I batch transcribe multiple audio files and save repeatable outputs?▼

Yes, you can transcribe single or multiple audio files using a bundled CLI tool. It applies deterministic defaults and outputs transcripts to designated output paths, ensuring repeatable transcription results across batches.

Do I need an OpenAI API key to convert speech to text with diarization?▼

Yes, converting speech to text requires the OPENAI_API_KEY environment variable to be set. The transcription process depends on OpenAI models to process audio files and generate diarized text outputs.

What output formats are supported when transcribing audio recordings?▼

Audio transcription supports text, JSON, and diarized JSON output formats. These formats allow you to store plain transcripts or structured speaker-labeled data for easier search, indexing, and accessibility.

How does the CLI handle long audio recordings during transcription?▼

The CLI uses chunking strategies to process long audio recordings during transcription. This breaks down large audio files into manageable segments for OpenAI models to transcribe without exceeding processing limits.

Related Skills

Explore More Content & Communication Skills→
storyclaw-officialstoryclaw-official

speech

Generate speech audio from text using the OpenAI Audio API.

Official
Intermediate
DanialHaseebDanialHaseeb

transcribe

Transcribe audio files into text or speaker-labeled JSON segments.

Community
Intermediate
kcns008kcns008
5

openai-whisper

Transcribe audio into text and subtitle files using the local Whisper CLI.

Community
Intermediate
adbertramadbertram
3

whisper-cli

Transcribe local audio and video files into timestamped JSON transcripts using whisper.cpp.

Community
Intermediate