elevenlabs

Generate speech, sound effects, and music and manage voice agents via the ElevenLabs API.

Updated Dec 18, 2025
One-click install
npx skills add https://github.com/l0lxl0lw/dotfiles --skill elevenlabs-l0lxl0lw
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: elevenlabs
Source: https://github.com/l0lxl0lw/dotfiles/tree/main/ai/shared/skills/integrations/elevenlabs
Command: npx skills add https://github.com/l0lxl0lw/dotfiles --skill elevenlabs-l0lxl0lw

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Creating voiceovers, sound effects, music, or voice agents normally requires recording studios, voice actors, or manual work in the ElevenLabs dashboard. This Skill lets you perform all of those audio and voice operations directly through ElevenLabs MCP tools from a conversation. ## Core Features & Use Cases - Speech & Sound Generation: Convert text to speech with selected voices and models, generate sound effects from descriptions, and design new voices from text prompts. - Voice & Audio Processing: Clone voices from samples, transcribe audio, convert speech between voices, and isolate vocals from background noise. - Music & Conversational AI: Compose music from structured composition plans and create, configure, and monitor conversational AI agents including outbound calls. - Use Case: A podcaster needs an intro jingle and a narrated segment. The Skill creates a composition plan, generates the music, searches for a suitable voice, converts the script to speech, and plays both audio files back. ## Quick Start Use the elevenlabs skill to generate a spoken narration of this paragraph using a warm male voice and play it back.

Frequently Asked Questions about elevenlabs

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

FAQPage Schema
How do I convert text to speech with ElevenLabs?

Text to speech uses the text_to_speech tool with your text, a voice ID, and a model. Search for a voice first with search_voices or search_voice_library, then pick a model from list_models before generating.

How do I clone a voice from audio samples?

Voice cloning uses the voice_clone tool with audio samples you provide. Confirm you have rights to the samples first, since cloning a voice without permission is not allowed.

Can ElevenLabs generate music from a text description?

Yes, music generation works in two steps: create_composition_plan builds the structure, instruments, and mood, then compose_music generates the track from that plan. Always create the plan first for a well-structured result.

Does ElevenLabs support transcribing audio to text?

Yes, the speech_to_text tool transcribes an audio file to text. Pass the audio file path to the tool and it returns the transcription.

Why did my ElevenLabs audio generation fail?

Generation failures are often tied to subscription limits or usage quotas. Run check_subscription to view your account tier and usage limits, and verify the voice ID and model you passed are valid.

Can an ElevenLabs agent make outbound phone calls?

Yes, make_outbound_call initiates calls from a conversational agent using numbers from list_phone_numbers. Explicit user confirmation of the phone number and recipient is required before any call is placed.