speech-to-text

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

Transcribe audio to text with ElevenLabs Scribe v2 for transcripts and subtitles.

46.2k|5.7k|Updated Mar 29, 2026

Search Tags:#subtitles #transcription #multilingual #speech-to-text #diarization #scribe-v2

Ready to run

npx skills add https://github.com/calesthio/OpenMontage --skill speech-to-text-calesthio

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Transcribe audio to text using ElevenLabs Scribe v2 to turn speech into accurate transcripts and captions for videos, meetings, and accessibility.

Core Features & Use Cases

Transcription with timestamps: Generate word-level timing data for subtitles, captions, and search.
Speaker diarization and multilingual support: Distinguish speakers and handle 90+ languages with hints.
Batch and real-time processing: Transcribe uploaded files or stream audio in real time via the API.

Quick Start

Provide an audio file and optional model_id to obtain a transcription.

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 to text with word-level timestamps for subtitles?▼

Transcribe audio to text with word-level timestamps by providing an audio file to ElevenLabs Scribe v2, which generates transcripts with precise timing data for subtitles, captions, and search.

What is speaker diarization and does multilingual transcription support it?▼

Speaker diarization distinguishes individual speakers in an audio file. ElevenLabs Scribe v2 provides multilingual transcription with speaker diarization, supporting over 90 languages with language hints.

Can I transcribe audio in real time or do I need to upload files for batch processing?▼

You can transcribe audio in real time via streaming API or upload files for batch processing. ElevenLabs Scribe v2 supports both methods for meetings, interviews, and podcasts.

Does ElevenLabs Scribe work with client-side SDKs and server-side API usage?▼

Yes, ElevenLabs Scribe v2 works with both client-side SDKs and server-side API usage, allowing you to integrate speech-to-text transcription directly into your software architecture.

How do I handle transcription for multiple languages and apply language hints?▼

To handle transcription for multiple languages, apply language hints when submitting audio to ElevenLabs Scribe v2. This guides the speech-to-text model to accurately process audio across its 90+ supported languages.