speech-to-text

Name: speech-to-text
Availability: InStock
Author: 47thtechcorner

Transcribe audio and video files into text using the ElevenLabs Scribe v2 API.

21|9|Updated Jun 22, 2026

Search Tags:#subtitles #transcription #audio #elevenlabs #speech-to-text #diarization

Ready to run

npx skills add https://github.com/47thtechcorner/RayCodes_OpenMontage --skill speech-to-text-47thtechcorner

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: speech-to-text
Source: https://github.com/47thtechcorner/RayCodes_OpenMontage/tree/main/openmontage_engine/.agents/skills/speech-to-text
Command: npx skills add https://github.com/47thtechcorner/RayCodes_OpenMontage --skill speech-to-text-47thtechcorner

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires elevenlabs, python-dotenv, pydub, and includes references (resource) components.

What problem does it solve?

This Skill solves the challenge of converting spoken audio and video content into accurate, timestamped text, enabling efficient documentation and accessibility.

Core Features & Use Cases

Advanced Transcription: Utilizes Scribe v2 for high-accuracy transcription across 90+ languages.
Speaker Diarization: Automatically identifies and labels different speakers in multi-person audio.
Real-Time Streaming: Supports low-latency live transcription for voice agents and meetings.
Use Case: Use this to transcribe a recorded hour-long board meeting into a structured, speaker-labeled document for minutes and action items.

Quick Start

Use the speech-to-text skill to transcribe the audio file named meeting_recording.mp3 using the scribe_v2 model.

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 with speaker diarization?▼

To transcribe audio with speaker diarization, the Skill processes files using the ElevenLabs Scribe v2 API to automatically identify and label different speakers in multi-person audio recordings.

Can I generate word-level timestamps when transcribing video files?▼

Yes, word-level timestamp generation is supported during video and audio transcription, providing precise timing data for each spoken word using the Scribe v2 model.

Does speech-to-text transcription support real-time streaming for live meetings?▼

Real-time streaming is supported for low-latency live transcription, enabling dynamic voice agent interactions and meeting transcriptions as the audio is being captured.

Do I need an ElevenLabs API key to transcribe audio files?▼

Yes, a valid ELEVENLABS_API_KEY environment variable is required for authentication and API access to process any audio or video transcription tasks through the Scribe v2 model.

What languages does the Scribe v2 transcription model support?▼

The Scribe v2 model supports high-accuracy transcription across over 90 languages, allowing you to convert spoken audio and video content into text globally.

Can I batch process multiple audio files for transcription?▼

Batch processing is supported for audio transcription, allowing you to process multiple recorded files into structured, timestamped text documents efficiently.