skills.rest
valtterimelkko
valtterimelkkoCOMMUNITY
Explore all skills by this author →
GitHub

transcribe-audio

Transcribe audio files to text via a local Whisper service.

1|1|Updated Jun 11, 2026
Search Tags:#automation#transcription#whisper#audio#speech-to-text
One-click install
npx skills add https://github.com/valtterimelkko/agent-workflow-skills --skill transcribe-audio-valtterimelkko
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: transcribe-audio
Source: https://github.com/valtterimelkko/agent-workflow-skills/tree/main/skills/transcribe-audio
Command: npx skills add https://github.com/valtterimelkko/agent-workflow-skills --skill transcribe-audio-valtterimelkko

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill removes the friction of manual transcription by leveraging a local Whisper service to convert audio files into accurate text documents.

Core Features & Use Cases

  • Local Processing: Keeps your audio data private by running transcription on your own infrastructure.
  • Multi-format Support: Handles common audio formats including WAV, MP3, and M4A.
  • Use Case: Quickly generate transcripts from recorded interviews, podcasts, or voice notes for easier searching and analysis.

Quick Start

Use the transcribe-audio skill to process the file named meeting-recording.wav and save the output to a text file.

Frequently Asked Questions about transcribe-audio

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

FAQPage Schema
How do I transcribe speech to text from an audio file locally?▼

To transcribe speech to text locally, this skill sends audio files to a local Whisper ASR service endpoint, converting spoken audio into written text documents instantly without relying on external cloud APIs.

Can I transcribe MP3 and M4A audio files using Whisper?▼

Yes, you can transcribe MP3 and M4A audio files, as well as OGG, WAV, and WebM formats. The skill supports these common audio formats for English language speech recognition.

Do I need a running Whisper service to convert audio recordings to text?▼

Yes, you need a running Whisper service at localhost:9000 and curl installed for HTTP communication. The skill acts as a client that sends audio data to this local endpoint for speech-to-text processing.

What is the best way to generate transcripts from podcasts and voice notes?▼

The best way to generate transcripts from podcasts and voice notes is using a local Whisper service, which keeps your audio data private on your own infrastructure while producing accurate searchable text outputs.

Does local speech-to-text transcription support languages other than English?▼

Currently, the local speech-to-text transcription supports English language speech only. The skill processes audio files by sending them to the Whisper ASR endpoint configured for English transcription.

Related Skills

Explore More Content & Communication Skills→
openclaw-easyopenclaw-easy
14

openai-whisper-api

Transcribe local audio files to text via the OpenAI Whisper API.

Community
Intermediate
aresbitaresbit
46

summarize

Summarize URLs, local files, and video transcripts into concise summaries.

Community
Intermediate
mangiapanejohn-devmangiapanejohn-dev
34

openai-whisper

Transcribe audio files to text locally using the Whisper CLI.

Community
Basic
brikkoAIbrikkoAI
1

openai-whisper

Transcribe local audio files to text using the Whisper CLI.

Official
Basic