skills.rest
skaile-ai
skaile-aiOFFICIAL
Explore all skills by this author →
WebsiteGitHub

use-elevenlabs

Convert Markdown dialogue to audio via the ElevenLabs v3 Dialogue API.

Updated Mar 28, 2026
Search Tags:#automation#markdown#dialogue#audio#podcast#tts#voice-mapping
One-click install
npx skills add https://github.com/skaile-ai/ai-assets --skill use-elevenlabs
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: use-elevenlabs
Source: https://github.com/skaile-ai/ai-assets/tree/main/use/skills/use-elevenlabs
Command: npx skills add https://github.com/skaile-ai/ai-assets --skill use-elevenlabs

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires elevenlabs, python-dotenv, pyyaml, and includes scripts (resource) and assets (resource) components.

What problem does it solve?

This skill enables turning markdown-scripted dialogue into audio using ElevenLabs, removing the manual steps of voice recording or external editing and enabling scalable audio generation from text.

Core Features & Use Cases

  • Single-voice TTS and multi-voice dialogue support via a structured Markdown workflow.
  • Voice mapping via host profiles; convert Markdown dialogue to a JSON manifest and call ElevenLabs v3 Dialogue API.
  • Environment-variable managed authentication with ELEVENLABS_API_KEY; supports .env files; includes modular scripts (text_to_speech.py, md_to_json.py, dialog_to_speech.py). Use cases include podcasting, character-based scenes, and automated audio production.

Quick Start

Convert a Markdown dialogue into spoken audio by running the provided workflow with your Markdown file and your ElevenLabs API key.

Frequently Asked Questions about use-elevenlabs

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

FAQPage Schema
How do I convert Markdown dialogue to audio using ElevenLabs?▼

You can convert Markdown dialogue to audio by running a workflow that transforms the text into a JSON manifest and calls the ElevenLabs v3 Dialogue API. This process supports both single-voice TTS and multi-voice scenarios.

Can I map different podcast voices to specific hosts in a Markdown script?▼

Yes, you can map voices to specific hosts using host profiles within the Markdown dialogue script. The workflow converts this mapping into a JSON manifest that dictates voice assignments for the ElevenLabs API.

Do I need an ElevenLabs API key to generate text to speech from Markdown?▼

Yes, you need an ELEVENLABS_API_KEY set in your environment or stored in a .env file to authenticate the text to speech requests. The Python scripts use this key to access the ElevenLabs v3 API.

What is the best way to automate multi-voice dialogue generation from Markdown?▼

The best way to automate multi-voice dialogue generation is using the provided Python scripts, which parse Markdown into JSON and route it to the ElevenLabs v3 Dialogue API. This removes manual voice recording and editing steps.

What Python dependencies are required to run the Markdown to audio workflow?▼

The Markdown to audio workflow requires the elevenlabs, python-dotenv, and pyyaml Python dependencies. These packages handle API communication, environment variable loading, and YAML parsing respectively.

Related Skills

Explore More Content & Communication Skills→
vibecodevibecode
1

ElevenLabs

Generate speech, sound effects, and transcriptions via the ElevenLabs API.

Official
Advanced
gauravb4875-uxgauravb4875-ux

podcast-generator

Generate podcast scripts and ElevenLabs audio from given topics.

Community
Advanced
akselikorhonen-siiliakselikorhonen-siili

qwen3-tts

Convert text into speech audio with voice cloning and customization modes.

Community
Basic
different-aidifferent-ai
63

eleven-labs-podcast

Generate podcast audio from text files using the ElevenLabs API.

Official
Intermediate