What audio formats does the ElevenLabs skill support?

It supports a variety of formats including MP3 (up to 192kbps), PCM (up to 44.1kHz), and uLaw (8kHz) for telecommunications use cases.

How do I connect my ElevenLabs account to this skill?

Add the Composio MCP server (https://rube.app/mcp) to your client and provide your ElevenLabs API key when prompted for authentication.

Is there a limit to how much text I can convert at once?

Yes, limits depend on the model used. Most models cap at 10,000-20,000 characters, while newer models like Flash and v2.5 support up to 40,000 characters.

How do I access the generated audio files?

The skill returns a presigned S3 URL valid for approximately one hour. You should download the file promptly using that link.

Can I use specific voices or models?

Yes, you can use the GET_VOICES and GET_MODELS tools to find the specific voice_id and model_id required for your synthesis request.

ElevenLabs Voice Automation

Name: ElevenLabs Voice Automation
Author: hameed0342j

byhameed0342j

0•

Content Management

Automates high-quality AI text-to-speech workflows, including voice management and audio streaming, directly within Claude.

The ElevenLabs Automation skill empowers Claude to interact directly with the ElevenLabs API, enabling the generation of natural-sounding speech from text using advanced AI models. It streamlines the entire audio production lifecycle by allowing users to browse voice libraries, inspect voice settings, monitor subscription credits, and retrieve historical generations. Whether you are building voice-enabled applications or automating content creation, this skill provides a robust interface for professional-grade voice synthesis and low-latency delivery.

Key Features

010 GitHub stars

02High-fidelity text-to-speech generation using ElevenLabs models

03Voice library browsing and detailed attribute inspection

04Subscription credit and usage monitoring to manage costs

05Historical audio retrieval for re-downloading previous generations

06Low-latency audio streaming for real-time delivery

Use Cases

01Building interactive AI agents with realistic vocal responses

02Automating voiceover production for marketing videos and educational content

03Generating multilingual audio assets for global application localization

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add hameed0342j/svh elevenlabs-automation

For use in Claude.ai and ChatGPT

Key Features

010 GitHub stars

02High-fidelity text-to-speech generation using ElevenLabs models

03Voice library browsing and detailed attribute inspection

04Subscription credit and usage monitoring to manage costs

05Historical audio retrieval for re-downloading previous generations

06Low-latency audio streaming for real-time delivery

Use Cases

01Building interactive AI agents with realistic vocal responses

02Automating voiceover production for marketing videos and educational content

03Generating multilingual audio assets for global application localization

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add hameed0342j/svh elevenlabs-automation

For use in Claude.ai and ChatGPT