skills.rest
shige1014-dev
shige1014-devCOMMUNITY
Explore all skills by this author →
GitHub

speech-to-text

Transcribe audio files into timestamped text with word-level timing.

1|Updated Apr 11, 2026
Search Tags:#real-time#transcription#multilingual#timestamps#speech-to-text#diarization
One-click install
npx skills add https://github.com/shige1014-dev/backup-OpenMontage --skill speech-to-text-shige1014-dev
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: speech-to-text
Source: https://github.com/shige1014-dev/backup-OpenMontage/tree/main/.agents/skills/speech-to-text
Command: npx skills add https://github.com/shige1014-dev/backup-OpenMontage --skill speech-to-text-shige1014-dev

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Transcribe audio to text with high accuracy, enabling subtitles, searchable transcripts, and accessible content from multimedia sources.

Core Features & Use Cases

  • Transcription in 90+ languages with word-level timestamps and optional speaker diarization for multi-speaker content.
  • Generate subtitles, meeting transcripts, and content archives from audio and video files.
  • Integration-ready with ElevenLabs Scribe v2 API for scalable batch or real-time transcription.

Quick Start

Provide an audio or video file and specify the model_id to receive a transcript with timestamps.

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 audio into text with word-level timestamps?▼

To transcribe audio with word-level timestamps, provide an audio or video file and specify the model_id. The Skill uses ElevenLabs Scribe v2 to return accurate, time-coded text suitable for subtitles or meeting archives.

Does speech-to-text transcription support multi-speaker diarization?▼

Yes, speech-to-text transcription supports optional speaker diarization for multi-speaker content. This feature identifies and separates individual speakers, generating structured transcripts with accurate word-level timestamps for meetings.

Can I transcribe audio files in multiple languages?▼

Yes, audio transcription supports over 90 languages, enabling you to generate searchable transcripts and accessible content from multimedia sources. You receive accurate text with word-level timestamps regardless of the input language.

Do I need an API key to generate subtitles from audio?▼

Yes, generating subtitles from audio requires internet access and an ElevenLabs API key to use Scribe v2. Once configured, you can process audio and video files to create content archives with time-coded text.

What is the best way to create meeting transcripts from video files?▼

Creating meeting transcripts from video files is best handled by submitting the multimedia file to the transcription model. It returns searchable text with word-level timestamps and optional diarization for multi-speaker identification.

Related Skills

Explore More Content & Communication Skills→
ri-ruri-ru

speech-to-text

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

Community
Advanced
ruiyangruiyiruiyangruiyi

whisper

Transcribe spoken audio into timestamped text or English translations.

Community
Intermediate
framerslabframerslab

diarization

Identify and label individual speakers in multi-speaker audio streams.

Official
Advanced
elevenlabselevenlabs
412

speech-to-text

Transcribe audio to text using ElevenLabs Scribe v2.

Official
Intermediate