asr

Transcribe audio from video or audio files using ASR providers.

4|Updated Jan 28, 2026
One-click install
npx skills add https://github.com/hwj123hwj/custom-skills --skill asr-hwj123hwj
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: asr
Source: https://github.com/hwj123hwj/custom-skills/tree/main/skills/asr
Command: npx skills add https://github.com/hwj123hwj/custom-skills --skill asr-hwj123hwj

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python, ffmpeg, pypdf, and includes scripts (resource) and assets (resource) components.

What problem does it solve?

Transcribing audio and video files into text manually is time-consuming. This Skill automates this process, allowing for quick and efficient transcription.

Core Features & Use Cases

  • Unified ASR with Pluggable Providers: Supports various ASR backends including SiliconFlow.
  • Audio Extraction: Automatically extracts audio from video files.
  • Use Case: Ideal for professionals or individuals who need to convert lengthy audio or video content into written text for easy access and reference.

Quick Start

Transcribe the content of 'presentation.wav' to text.

Frequently Asked Questions about asr

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

FAQPage Schema
How do I automatically transcribe audio from a video file to text?

To transcribe audio from a video file to text, you can use an ASR provider that automatically extracts the audio track and converts the spoken word into written text. This requires Python and ffmpeg.

What dependencies do I need to run an ASR audio transcription script?

To run ASR audio transcription, you need Python, ffmpeg for audio extraction from video files, pypdf, and a configured ASR provider backend such as SiliconFlow to process the speech recognition.

Can I use SiliconFlow as a pluggable ASR provider for content digitization?

Yes, you can use SiliconFlow as a pluggable ASR provider for content digitization. The system supports unified ASR with various pluggable backends to efficiently convert spoken word into text.

Is there a way to extract audio from video before processing speech recognition?

Yes, the transcription process includes automatic audio extraction from video files before processing speech recognition. This eliminates the need for manual audio separation prior to ASR transcription.

What is the best way to digitize lengthy educational video content into written text?

The best way to digitize lengthy educational video content into written text is using an automated ASR transcription tool. It extracts audio and converts spoken word into text for easy reference.