skills.rest
inho-team
inho-teamOFFICIAL
Explore all skills by this author →
GitHub

Qaudio-transcriber

Transcribe audio recordings into Markdown with speaker labels and meeting minutes.

6|Updated Mar 14, 2026
Search Tags:#markdown#subtitles#transcription#audio#speech-to-text#diarization#meeting-minutes
One-click install
npx skills add https://github.com/inho-team/qe-framework --skill qaudio-transcriber
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Qaudio-transcriber
Source: https://github.com/inho-team/qe-framework/tree/main/skills/Qaudio-transcriber
Command: npx skills add https://github.com/inho-team/qe-framework --skill qaudio-transcriber

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill converts audio recordings into structured Markdown outputs with rich metadata, meeting minutes, and subtitles, enabling clear, sharable documentation from meetings, interviews, and lectures.

Core Features & Use Cases

  • Auto-detection of transcription engines (faster-whisper or whisper) with automatic fallback.
  • Multi-format input support (MP3, WAV, M4A, OGG, FLAC, WEBM) and language detection.
  • Output includes speaker diarization, timestamps, meeting minutes, and subtitle formats (SRT/VTT) in Markdown.

Quick Start

Transcribe the given audio file to a Markdown report with speaker metadata and meeting minutes.

Frequently Asked Questions about Qaudio-transcriber

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

FAQPage Schema
How do I transcribe audio recordings into Markdown with speaker labels?▼

Transcribe audio into professional Markdown by using a speech-to-text engine that supports speaker diarization, timestamps, and meeting minutes generation for clear, structured documentation.

Can I use Whisper or faster-whisper to generate meeting minutes from audio files?▼

Yes, the transcription process auto-detects Whisper or faster-whisper engines to generate meeting minutes, applying automatic fallback to ensure accurate speech-to-text conversion from audio files.

Does audio transcription support multiple formats like MP3, WAV, and M4A?▼

Audio transcription supports multi-format inputs including MP3, WAV, M4A, OGG, FLAC, and WEBM, automatically detecting the spoken language to produce structured Markdown outputs.

How do I create subtitles and SRT files from recorded lectures or interviews?▼

Create subtitles from recorded lectures or interviews by transcribing the audio into subtitle formats like SRT or VTT, outputting the results within a structured Markdown file.

What is speaker diarization and when do I need it for speech-to-text transcription?▼

Speaker diarization identifies and labels individual speakers in an audio recording. You need it for meetings, interviews, or lectures to accurately attribute transcribed text to the correct participant.

Are there limitations when converting audio to Markdown for content analysis?▼

Limitations depend on the detected transcription engine, Whisper or faster-whisper, and audio input quality. Poor audio clarity or unsupported formats outside MP3, WAV, M4A, OGG, FLAC, and WEBM may impact transcription accuracy.

Related Skills

Explore More Content & Communication Skills→
pramudityadpramudityad

transcribe

Transcribe audio files to plain text using the Groq Whisper API.

Community
Basic
ricoismericoisme

srt-to-vtt

Convert SRT subtitle files to VTT format with encoding and language detection.

Community
Basic
seb1nseb1n
147

meeting-transcription

Transcribe meeting audio with speaker diarization and generate action items.

Community
Advanced
QcasaresQcasares

elevenlabs-stt

Transcribe audio to text using ElevenLabs' Scribe v2 API.

Community
Intermediate