skills.rest
ChatAndBuild
ChatAndBuildOFFICIAL
Explore all skills by this author →
Website𝕏@chatandbuildGitHub

transcribe

Transcribe audio files to text with optional speaker diarization via OpenAI API.

1|12|Updated Feb 23, 2026
Search Tags:#audio transcription#diarization#speech to text#meeting summary#interview transcription
One-click install
npx skills add https://github.com/ChatAndBuild/chatchat-skills --skill transcribe-chatandbuild
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: transcribe
Source: https://github.com/ChatAndBuild/chatchat-skills/tree/main/skills/transcribe
Command: npx skills add https://github.com/ChatAndBuild/chatchat-skills --skill transcribe-chatandbuild

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill addresses the need for efficient and accurate transcription of audio files, making it easy to convert speech to text without manual transcription.

Core Features & Use Cases

  • Audio Transcription: Convert spoken language to text.
  • Optional Diarization: Identify and label different speakers in a recording.
  • Known Speaker Hints: Provide speaker identification with references to audio samples.
  • Use Case: For anyone who needs to convert recorded speeches, interviews, or meetings into text for reference or sharing.

Quick Start

Run the transcribe command with the path to your audio file: python3 /path/to/skill/scripts/transcribe_diarize.py /path/to/your/audio.wav.

Frequently Asked Questions about transcribe

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

FAQPage Schema
How do I transcribe an audio file to text with speaker diarization?▼

Audio transcription with speaker diarization converts recorded speech to text while labeling different speakers. You can run the transcription script directly on audio files to automatically generate text and identify who is speaking.

What audio formats can I use for speech to text conversion?▼

Speech to text conversion supports mp3, mp4, mpga, m4a, wav, and webm audio formats. You provide a supported file path to the transcription script to process the audio into text.

Can I identify known speakers in an interview transcription?▼

Interview transcription supports known speaker identification using audio sample references. You provide hints mapped to reference audio, allowing the system to label specific speakers during the transcription process.

Does OpenAI handle meeting transcription and summarization workflows?▼

OpenAI handles meeting transcription by automating audio to text conversion. The transcribed text output can then be used directly for meeting summarization and speaker identification workflows.

What's the best way to convert recorded meetings into text?▼

Converting recorded meetings into text is best handled by automated speech to text transcription. Running a transcription script on the meeting audio file yields accurate text output with optional diarization for multiple speakers.

Related Skills

Explore More Product & Management Skills→
team-telnyxteam-telnyx
3

telnyx-stt

Transcribe MP3, WAV, OGG, M4A, and WebM audio files via the Telnyx Speech-to-Text API.

Official
Basic
zm2231zm2231

session-summary

Generate structured markdown summaries of work sessions with outcomes, decisions, action items, and learnings.

Community
Advanced
yoonhwanyoonhwan
3

yt-transcribe

Transcribes and summarizes YouTube videos using local speech-to-text tools.

Community
Intermediate
eachlabseachlabs
28

eachlabs-voice-audio

Convert text to speech and transcribe audio with speaker diarization.

Official
Advanced