skills.rest
jlenrique
jlenriqueCOMMUNITY
Explore all skills by this author →
GitHub

elevenlabs-audio

Automate ElevenLabs audio production with narration, timestamps, and WebVTT output.

Updated Mar 26, 2026
Search Tags:#dialogue#elevenlabs#timestamps#narration#sound-effects#pronunciation-dictionary
One-click install
npx skills add https://github.com/jlenrique/course-DEV-IDE-with-AGENTS --skill elevenlabs-audio
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: elevenlabs-audio
Source: https://github.com/jlenrique/course-DEV-IDE-with-AGENTS/tree/main/skills/elevenlabs-audio
Command: npx skills add https://github.com/jlenrique/course-DEV-IDE-with-AGENTS --skill elevenlabs-audio

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

ElevenLabs audio mastery skill with narration generation, timestamp extraction, WebVTT companion output, manifest-driven narration write-back, pronunciation dictionary creation, dialogue generation, sound effects, and music composition through the shared ElevenLabsClient. This skill serves as the voice-production layer in the repo's three-layer architecture: Voice Director (agent judgment) -> elevenlabs-audio (skill - tool expertise) -> ElevenLabsClient (API client - connectivity).

Core Features & Use Cases

  • Narration generation with optional timestamps and corresponding WebVTT output.
  • Manifest-driven narration workflows with write-back to lesson assets.
  • Pronunciation dictionary creation and management for medical terminology.
  • Dialogue generation, sound effects (SFX), and music composition wrappers.
  • Style-guide-driven defaults and voice-preview integration to support consistent production.

Quick Start

Generate a narrated lesson using ElevenLabs with timestamps, pronunciation dictionaries, dialogue, SFX, and music wrappers.

Frequently Asked Questions about elevenlabs-audio

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

FAQPage Schema
How do I generate medical education narration with synchronized timestamps using ElevenLabs?▼

Automate medical education narration generation with timestamps by running manifest-driven workflows that produce audio alongside WebVTT companion files and write back directly to lesson assets.

How do I create a pronunciation dictionary for medical terminology in ElevenLabs audio?▼

Create a pronunciation dictionary for medical terminology through the ElevenLabsClient to define and manage specialized term pronunciations, ensuring accurate voice output for complex medical education content.

Can I add dialogue, sound effects, and music to ElevenLabs narration automatically?▼

Yes, you can generate dialogue, sound effects, and music wrappers automatically alongside ElevenLabs narration using the shared ElevenLabsClient to integrate multi-layer audio into medical education content.

What is a manifest-driven narration workflow for automated audio production?▼

A manifest-driven narration workflow uses a configuration file to define audio production parameters, enabling automated generation of ElevenLabs narration with write-back capabilities to update lesson assets directly.

Do I need python-dotenv and PyYAML to run ElevenLabs audio automation scripts?▼

Yes, you need python-dotenv and PyYAML dependencies to configure environment variables and parse YAML manifests required by the ElevenLabs audio automation scripts and style-guide defaults.

How do style-guide defaults and voice previews work in ElevenLabs audio production?▼

Style-guide defaults apply consistent voice parameters across narration and dialogue generation, while operator previews allow you to test ElevenLabs audio output before committing to full manifest-driven production.

Related Skills

Explore More Education & Research Skills→
minicooheiminicoohei
345

proofreading-agent

Detect typos and grammar issues in Japanese articles with inline annotations.

Community
Intermediate
himanshu231204himanshu231204
2

video-editing

Automate raw footage editing into platform-ready videos with FFmpeg and Remotion.

Community
Intermediate
digitalsambadigitalsamba
1.9k

elevenlabs

Generate AI voiceovers, sound effects, and music via ElevenLabs APIs.

Official
Intermediate
MuhammadUAMuhammadUA

elevenlabs

Generate speech, cloned voices, and sound effects via the ElevenLabs API.

Community
Intermediate