What audio formats are supported by this ElevenLabs skill?

It supports various formats including MP3 (up to 192kbps for Creator tier), PCM (up to 44.1kHz for Pro tier), and uLaw (8000Hz) specifically for telephony integrations like Twilio.

Can I use this skill to generate long-form audio content?

Yes, though models typically have a character limit per request (up to 40,000 for v2.5). For very long texts, it is best practice to split the input into chunks of approximately 5,000 characters.

Does this skill support real-time audio delivery?

Yes, the ELEVENLABS_TEXT_TO_SPEECH_STREAM tool is designed for low-latency playback, though it is not compatible with the specific eleven_v3 model.

How do I handle 'quota exceeded' errors?

You can use the ELEVENLABS_GET_USER_SUBSCRIPTION_INFO tool to check your remaining credits and plan limits before starting a large batch of generation tasks.

How do I find the correct Voice ID for synthesis?

You can use the ELEVENLABS_GET_VOICES tool to list all available voices in your library. This returns the names, attributes, and unique IDs required for speech generation.

ElevenLabs Automation

Name: ElevenLabs Automation
Author: ComposioHQ

byComposioHQ

•

47,561

•

生产力与工作流

Automates text-to-speech workflows using ElevenLabs to generate natural-sounding audio, manage voices, and track usage.

This skill integrates ElevenLabs' industry-leading AI voice technology into Claude, enabling developers to programmatically generate high-fidelity audio from text. It provides comprehensive control over the speech synthesis process, allowing you to browse an extensive voice library, select optimized models for different languages, and manage subscription credits. Whether you are building real-time voice assistants or automated content generation pipelines, this skill simplifies the integration of low-latency streaming and historical audio retrieval directly into your AI-driven workflows.

主要功能

01Comprehensive voice management to browse, filter, and inspect voices by accent, gender, and use case.

02Historical audio retrieval for re-downloading previously generated speech items.

0347,561 GitHub stars

04High-fidelity text-to-speech generation with multiple output formats like MP3, PCM, and uLaw.

05Built-in subscription monitoring to track credit usage and plan limits programmatically.

06Low-latency audio streaming capabilities for real-time application responsiveness.

使用场景

01Developing real-time AI voice agents for customer service or interactive applications.

02Enhancing application accessibility by converting written documentation into spoken word.

03Automating narration for video content, podcasts, and social media posts.

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add composiohq/awesome-claude-skills elevenlabs-automation

For use in Claude.ai and ChatGPT

Download Skill