elevenlabs-stt

Transcribe audio and video files via the ElevenLabs Scribe API with context-aware post-processing.

8|Updated Jul 26, 2026

Search Tags:#transcription #audio #elevenlabs #speech-to-text #post-processing #correction

Ready to run

npx skills add https://github.com/joonlab/joonlab-claudecode-setting-for-share --skill elevenlabs-stt-joonlab

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: elevenlabs-stt
Source: https://github.com/joonlab/joonlab-claudecode-setting-for-share/tree/main/claude/skills/elevenlabs-stt
Command: npx skills add https://github.com/joonlab/joonlab-claudecode-setting-for-share --skill elevenlabs-stt-joonlab

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This skill solves the common issue of inaccurate speech-to-text transcriptions, particularly regarding technical jargon, proper nouns, and domain-specific terminology that standard AI models often misinterpret.

Core Features & Use Cases

Context-Aware Correction: Uses your project memory and glossary to automatically fix transcription errors, ensuring high-quality output without manual editing.
Multi-Stage Pipeline: Combines ElevenLabs Scribe API transcription with a Claude-powered sub-agent for intelligent post-processing and structural verification.
Use Case: Perfect for transcribing technical meetings, interviews, or lectures where accurate terminology and speaker identification are critical for documentation.

Quick Start

Use the elevenlabs-stt skill to transcribe the audio file located at path/to/recording.mp3 and apply context-aware corrections.

Frequently Asked Questions about elevenlabs-stt

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

FAQPage Schema

How do I transcribe audio files and fix technical jargon errors automatically?▼

To transcribe audio files and fix technical jargon automatically, this skill uses the ElevenLabs Scribe API for initial speech-to-text conversion, then applies a Claude-powered sub-agent for context-aware post-processing to correct domain-specific terminology.

Can I use my own glossary to correct speech-to-text transcriptions?▼

Yes, you can use local memory or glossary files to correct speech-to-text transcriptions. The skill dynamically injects this context to identify and fix misinterpreted proper nouns and technical terms during the automated post-processing stage.

Does the ElevenLabs Scribe API support transcribing technical meetings with speaker identification?▼

Yes, the ElevenLabs Scribe API supports transcribing technical meetings with speaker identification. It processes the audio recording and the skill's pipeline applies structural verification to ensure accurate documentation for interviews or lectures.

What is context-aware speech-to-text post-processing and when do I need it?▼

Context-aware speech-to-text post-processing is a secondary correction stage that uses project memory to fix transcription errors. You need it when standard AI models misinterpret technical jargon, proper nouns, or domain-specific terminology in your audio files.

Do I need an active ElevenLabs API key to transcribe video files into text?▼

Yes, you need an active ElevenLabs API key to transcribe video files into text. The skill relies on the Scribe API for the initial transcription stage before applying its automated context-aware corrections to the output.

Why does my transcription contain misinterpreted domain-specific terminology?▼

Your transcription contains misinterpreted domain-specific terminology because standard AI speech-to-text models often lack project context. This skill solves the issue by applying context-aware post-processing using your local glossary files to automatically correct the errors.