transcribe

Transcribe audio and video files into text, JSON, SRT, or VTT using GROQ API.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/larsboes/pai-marketplace --skill transcribe-larsboes
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: transcribe
Source: https://github.com/larsboes/pai-marketplace/tree/main/marketplace/plugins/content/skills/transcribe
Command: npx skills add https://github.com/larsboes/pai-marketplace --skill transcribe-larsboes

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Transcribing audio and video content into accurate, searchable text to simplify note-taking, accessibility, and content analysis.

Core Features & Use Cases

  • Supports multiple input formats (audio and video) and outputs (text, json, srt, vtt) for transcripts and captions.
  • Batch processing for converting many files efficiently, with optional parallelism.
  • Suitable for meetings, podcasts, lectures, interviews, and media archives that require searchable transcripts or subtitles.

Quick Start

Run transcribe.mjs meeting.m4a to produce a plain-text transcript.

Frequently Asked Questions about transcribe

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

FAQPage Schema
How do I transcribe audio from a podcast or lecture into text?

To transcribe audio from podcasts or lectures into text, the tool processes audio files and outputs searchable plain text. It uses the GROQ speech-to-text API to convert spoken content into accurate written transcripts.

Do I need a GROQ API key to convert video to subtitles?

Yes, a GROQ API key is required to convert video to subtitles. The tool uses curl to make API calls to GROQ's speech-to-text endpoint, generating SRT or VTT subtitle files from your media content.

Can I batch process multiple audio files for transcription?

Yes, you can batch process multiple audio files for transcription. The tool supports batch processing with optional parallelism to efficiently convert large archives of meetings or interviews into text, JSON, or subtitle formats.

What is the best way to get SRT subtitles from an m4a file?

The best way to get SRT subtitles from an m4a file is running the transcription script with the file as an argument. It outputs structured subtitle formats like SRT or VTT by leveraging the GROQ speech-to-text API.

Does speech-to-text transcription support translating audio into another language?

Yes, speech-to-text transcription supports optional translation. Alongside specifying the original language, the tool can translate spoken audio or video content into text while processing files via the GROQ API.