Is real-time audio streaming supported?

Yes, the skill includes specific implementation patterns for the ElevenLabs streaming endpoint to facilitate real-time audio playback.

Can I use my own custom cloned voices?

Yes, by listing available voices you can retrieve the IDs for your custom cloned voices and use them for text-to-speech generation.

Which ElevenLabs models can I use?

The skill supports all ElevenLabs models, including eleven_multilingual_v2 for maximum quality and eleven_flash_v2_5 for low-latency applications.

How do I authenticate this skill with ElevenLabs?

You need to sign up at elevenlabs.io, generate an API key from your profile settings, and store it in an environment variable named ELEVENLABS_API_KEY.

What audio formats are supported?

You can output audio in various formats including MP3 (128kbps or 192kbps) and PCM at sample rates of 16kHz, 22.05kHz, or 24kHz.

ElevenLabs Voice AI

Name: ElevenLabs Voice AI
Author: vm0-ai

byvm0-ai

•

生产力与工作流

Generates ultra-realistic AI speech from text using the ElevenLabs API directly within your terminal workflow.

关于

The ElevenLabs skill provides a robust interface for integrating high-fidelity AI voice synthesis into your development environment via Claude Code. It enables developers to list available voices, select between various performance models like Multilingual v2 or Flash v2.5, and generate high-quality audio files or streams. With granular control over voice settings such as stability and similarity boost, this skill is perfect for automating voiceovers, enhancing accessibility, and building sophisticated audio-driven applications without leaving the command line.

主要功能

Support for low-latency streaming and multiple output formats (MP3, PCM)
Comprehensive voice management for premade, cloned, and generated voices
Granular control over voice stability and similarity settings
18 GitHub stars
Built-in subscription and usage monitoring to track character limits
Realistic text-to-speech generation using advanced AI models

使用场景

Integrating AI-driven accessibility features into application prototypes
Automating high-quality voiceover production for videos and podcasts
Developing real-time conversational agents and interactive audio experiences

关于

主要功能

Support for low-latency streaming and multiple output formats (MP3, PCM)
Comprehensive voice management for premade, cloned, and generated voices
Granular control over voice stability and similarity settings
18 GitHub stars
Built-in subscription and usage monitoring to track character limits
Realistic text-to-speech generation using advanced AI models

使用场景

Integrating AI-driven accessibility features into application prototypes
Automating high-quality voiceover production for videos and podcasts
Developing real-time conversational agents and interactive audio experiences