audio

Convert text input into synthesized speech using the ElevenLabs API.

6|2|Updated Jan 29, 2026

Search Tags:#voice #audio #elevenlabs #tts #narration #speech

Ready to run

npx skills add https://github.com/filipexyz/ravi --skill audio-filipexyz

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: audio
Source: https://github.com/filipexyz/ravi/tree/main/src/plugins/internal/ravi-system/skills/audio
Command: npx skills add https://github.com/filipexyz/ravi --skill audio-filipexyz

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill solves the friction of converting text-based content into professional-grade spoken audio, enabling seamless integration of voice generation into agent workflows.

Core Features & Use Cases

Text-to-Speech Generation: Convert any text or markdown file into high-quality audio using ElevenLabs.
Customizable Output: Control voice identity, speech speed, language, and output formats to match specific project needs.
Direct Delivery: Automatically send generated audio files directly to chat sessions or save them to local storage.

Quick Start

Use the audio skill to generate a spoken version of the text Hello world using the default voice settings.

Frequently Asked Questions about audio

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

FAQPage Schema

How do I convert text to speech using ElevenLabs for narration?▼

You can generate spoken audio by passing text input to the ElevenLabs API. The skill processes your text using configured voice parameters and returns high-fidelity synthesized speech suitable for automated narration and podcast creation.

Do I need an ElevenLabs API key to generate TTS audio?▼

Yes, a valid ElevenLabs API key is required to generate TTS audio. You must configure this key along with voice parameters to ensure the API successfully processes your text input and returns high-fidelity synthesized speech.

Can I customize voice identity and speech speed for generated audio?▼

Yes, you can control voice identity, speech speed, language, and output formats. Configuring these voice parameters ensures the synthesized speech matches your specific project needs for narration, voice messages, or podcast creation.

What is the best way to create podcast audio from markdown files?▼

Generating podcast audio from markdown requires a TTS API like ElevenLabs. You submit the markdown text, configure voice settings, and the API produces high-quality spoken audio files ready for direct delivery or local storage.

Can generated speech be sent directly to a chat session?▼

Yes, generated audio files can be sent directly to chat sessions or saved to local storage. This direct delivery mechanism enables seamless integration of synthesized voice messages into automated agent workflows.