speech-to-text

Name: speech-to-text
Availability: InStock
Author: StoryClaw

Transcribe audio files into text using ElevenLabs Scribe v2.

Updated Feb 11, 2026

Search Tags:#transcription #audio processing #elevenlabs #speech-to-text #voice to text #scribe

Ready to run

npx skills add https://github.com/storyclaw-official/storyclaw-assistant --skill speech-to-text-storyclaw-official

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: speech-to-text
Source: https://github.com/storyclaw-official/storyclaw-assistant/tree/main/skills/speech-to-text
Command: npx skills add https://github.com/storyclaw-official/storyclaw-assistant --skill speech-to-text-storyclaw-official

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill converts spoken audio into written text, making audio content searchable, editable, and accessible.

Core Features & Use Cases

Accurate Transcription: Utilizes ElevenLabs Scribe v2 for high-quality speech-to-text conversion across 90+ languages.
Advanced Features: Supports speaker diarization, word-level timestamps, and keyterm prompting for specialized vocabulary.
Use Case: Transcribe a recorded meeting to generate accurate minutes, create subtitles for a video, or convert a voice memo into a text document.

Quick Start

Use the speech-to-text skill to transcribe the audio file 'meeting_recording.mp3'.

Frequently Asked Questions about speech-to-text

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

FAQPage Schema

How do I transcribe an audio file to text with AI?▼

To transcribe audio to text, this Skill processes your audio files using the ElevenLabs Scribe v2 model to generate accurate written text. It requires an internet connection and an ElevenLabs API key.

Can I identify different speakers when transcribing a recorded meeting?▼

Yes, speaker diarization is supported during transcription to identify and separate different speakers. This feature helps accurately attribute dialogue when generating meeting minutes or analyzing conversations.

Does this speech-to-text transcription support multiple languages?▼

The speech-to-text transcription supports over 90 languages using the ElevenLabs Scribe v2 model. You can also use keyterm prompting to improve accuracy for specialized vocabulary within those languages.

How do I add word-level timestamps to my transcribed audio?▼

You can generate word-level timestamps by processing your audio through the ElevenLabs Scribe v2 model. This provides precise timing data for applications like subtitle generation or detailed voice content analysis.

Do I need an API key to convert voice memos into a text document?▼

Yes, you need an active ElevenLabs API key and an internet connection to convert voice memos into text documents. The Skill relies on the ElevenLabs Scribe v2 model for all batch and real-time processing.