elevenlabs-voice

Generate speech and sound effects via the ElevenLabs API.

Updated Feb 14, 2026
One-click install
npx skills add https://github.com/Shakudo-io/opencode-skills --skill elevenlabs-voice
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: elevenlabs-voice
Source: https://github.com/Shakudo-io/opencode-skills/tree/main/elevenlabs-voice
Command: npx skills add https://github.com/Shakudo-io/opencode-skills --skill elevenlabs-voice

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

ElevenLabs Voice AI enables ultra-low latency text-to-speech and AI sound effects generation, enabling real-time voice interactions and rich audio assets.

Core Features & Use Cases

  • Ultra-low latency Flash v2.5 TTS (~75ms) for real-time conversations and Twilio integration
  • Multilingual TTS options with high-quality voice profiles and streaming
  • AI sound effects generation for sound design, game audio, and UI alerts

Quick Start

Instantiate requests to ElevenLabs endpoints with your API key to generate speech or sound effects from text, then stream or save the output in your app.

Frequently Asked Questions about elevenlabs-voice

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

FAQPage Schema
How do I add ultra-low-latency text-to-speech to a real-time chatbot?

Ultra-low-latency text-to-speech for real-time chatbots is achieved using the ElevenLabs Flash v2.5 model. This Skill automates requests to streaming endpoints, delivering approximately 75ms latency for immediate natural voice responses in conversational applications.

Can I use AI voice synthesis for Twilio phone call integrations?

AI voice synthesis works with Twilio integrations by applying the Flash v2.5 model's ultra-low latency. This Skill automates endpoint requests and audio streaming to ensure immediate, natural audio output required for responsive telephony applications.

How do I generate AI sound effects from text for game audio?

Generating AI sound effects from text for game audio involves instantiating requests to ElevenLabs endpoints. This Skill specifies usage requirements for API key management, model selection, and output formats to stream or save generated sound assets.

Does this text-to-speech Skill support multilingual voice generation?

Multilingual text-to-speech is supported through high-quality voice profiles and streaming options. This Skill automates the synthesis process, specifying model selection and endpoint configurations to deliver natural audio across various languages.

What is the best way to handle errors during real-time audio streaming?

Handling errors during real-time audio streaming requires robust error handling logic as documented in the Skill. It specifies usage requirements for managing API keys, streaming endpoints, and output formats to ensure reliable voice synthesis operations.

Do I need an API key to generate speech or sound effects from text?

An API key is required to instantiate requests to ElevenLabs endpoints for generating speech or sound effects. This Skill specifies API key management, streaming endpoints, and output formats to securely stream or save the audio output in your app.