skills.rest
video-production-buddy
video-production-buddyOFFICIAL
Explore all skills by this author →
WebsiteGitHub

speech-to-text

Transcribe audio and video files into timestamped text with speaker labels.

602|12|Updated Apr 22, 2026
Search Tags:#subtitles#transcription#elevenlabs#speech-to-text#audio-processing#real-time-transcription#speaker-diarization
One-click install
npx skills add https://github.com/video-production-buddy/video-production-buddy --skill speech-to-text-video-production-buddy
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: speech-to-text
Source: https://github.com/video-production-buddy/video-production-buddy/tree/main/.agents/local/skills/speech-to-text
Command: npx skills add https://github.com/video-production-buddy/video-production-buddy --skill speech-to-text-video-production-buddy

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Manual transcription of audio and video content is slow, expensive, and prone to human error, especially for long recordings, multi-speaker meetings, or content in less common languages. This Skill automates accurate transcription with optional speaker labels and timestamps, reducing transcription time from hours to minutes.

Core Features & Use Cases

  • Multi-Language Batch Transcription: Convert pre-recorded audio or video files up to 10 hours long to text, with support for 90+ languages and custom keyterms to boost accuracy for domain-specific jargon like product names or technical terms.
  • Speaker Diarization & Timestamped Output: Automatically identify different speakers and generate word-level timestamps for use in subtitles, meeting notes, or video editing workflows.
  • Real-Time Live Transcription: Stream live audio with ultra-low latency (~150ms) for use cases like live captioning, voice agent backends, or real-time meeting note taking.

Quick Start

Use the speech-to-text skill to transcribe the attached team meeting recording 'q3-sync.mp3' and output a timestamped transcript with speaker labels separated by speaker ID.

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 multi-speaker audio with timestamps?▼

To transcribe multi-speaker audio with timestamps, process pre-recorded files up to 10 hours long to generate word-level timestamps and speaker diarization labels across 90+ supported languages.

Do I need an ElevenLabs API key for speech-to-text transcription?▼

Yes, an active ElevenLabs API key and internet access are required to perform speech-to-text transcription, enabling features like keyterm biasing and real-time low-latency streaming.

Can I use speech-to-text for live audio stream transcription?▼

Yes, you can stream live audio for real-time transcription with ultra-low latency around 150ms, supporting live captioning, voice agent backends, and real-time meeting note generation.

How do I generate subtitles for long-form recordings?▼

Generate subtitles for long-form recordings by batch processing audio or video files up to 10 hours long, producing accurate timestamped text with optional multi-speaker labeling.

What is the best way to handle domain-specific jargon during transcription?▼

To handle domain-specific jargon during transcription, apply custom keyterms to boost accuracy for technical terms or product names within the ElevenLabs Scribe v2 processing workflow.

Related Skills

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

voice-isolator

Remove background noise and isolate speech from audio files via the ElevenLabs Voice Isolator API.

Community
Intermediate
hmzainjamilhmzainjamil
1

Transcription Automation

Convert audio and video recordings into transcripts, subtitles, and meeting notes.

Community
Advanced
video-dbvideo-db
116

videodb

Ingest, index, and stream video and audio via the VideoDB SDK.

Official
Advanced
QcasaresQcasares

elevenlabs-stt

Transcribe audio to text using ElevenLabs' Scribe v2 API.

Community
Intermediate