skills.rest
Gonglitian
GonglitianCOMMUNITY
Explore all skills by this author →
GitHub

audio-transcribe

Transcribe audio and video files into txt, json, and srt transcripts.

2|Updated Mar 20, 2026
Search Tags:#video#subtitles#transcription#yt-dlp#audio#gpu#faster-whisper
One-click install
npx skills add https://github.com/Gonglitian/agent-skills --skill audio-transcribe-gonglitian
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: audio-transcribe
Source: https://github.com/Gonglitian/agent-skills/tree/main/skills/audio-transcribe
Command: npx skills add https://github.com/Gonglitian/agent-skills --skill audio-transcribe-gonglitian

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Transcribe audio and video media into accurate, text-ready transcripts using a GPU-optimized pipeline, dramatically reducing manual transcription time and enabling searchable archives.

Core Features & Use Cases

  • High-accuracy transcription with smart parallel GPU scheduling for long files
  • Language handling and domain terminology injection to improve recognition quality
  • Batch processing and multiple outputs (txt, json, srt) for seamless downstream use

Quick Start

Run transcribe.py on a folder of audio files to generate transcripts in txt, json, and srt formats.

Frequently Asked Questions about audio-transcribe

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

FAQPage Schema
How do I transcribe audio from a video file into text subtitles?▼

To transcribe audio from a video file into text subtitles, you can use an automated Python-based pipeline with faster-whisper to extract speech and generate subtitle outputs.

Can I batch process multiple audio files for transcription?▼

Yes, you can batch process multiple audio files for transcription by running the automated workflow on a folder, which generates text, json, and srt outputs for each file.

Does faster-whisper support smart GPU scheduling for long audio files?▼

Faster-whisper supports smart parallel GPU scheduling for long audio files, optimizing hardware usage to dramatically reduce manual transcription time during processing.

How do I improve transcription accuracy for videos with domain terminology?▼

To improve transcription accuracy for videos with domain terminology, the pipeline uses language processing with domain-context injection to refine recognition quality for specialized vocabulary.

What output formats are supported when transcribing audio to text?▼

Supported output formats when transcribing audio to text include txt, json, and srt, allowing seamless downstream use for searchable archives and subtitle integration.

Do I need yt-dlp to transcribe video content into text?▼

You need yt-dlp to download video content into text pipelines, where it works alongside FFmpeg and faster-whisper to automate the extraction and transcription workflow.

Related Skills

Explore More Content & Communication Skills→
xingBaGanxingBaGan

video-understand

Analyze video content and transcribe audio locally with ffmpeg and Whisper.

Community
Intermediate
DavidTejuDavidTeju
9

speech-to-text

Transcribe audio files locally using whisper-cpp with Metal GPU acceleration.

Community
Intermediate
JulesDupsJulesDups

analyze-video

Download videos, transcribe audio locally, extract frames, and generate per-video syntheses with a cross-video recap.

Community
Advanced
x402agentx402agent

openai-whisper

Transcribe audio locally into text using the Whisper CLI.

Community
Basic