ElevenLabs
The official ElevenLabs MCP server brings state-of-the-art voice AI to agents: text-to-speech, speech-to-text, voice cloning and design, speech-to-speech conversion, sound-effect and music generation, audio isolation, and management of conversational AI agents and outbound phone calls.
Tools
add_knowledge_base_to_agent
Attach documents or text to an agent as knowledge.
compose_music
Generate background music from a text prompt or plan.
create_agent
Create a conversational AI agent with a custom voice and behavior.
create_composition_plan
Create a structured music plan without spending credits.
create_voice_from_preview
Save a generated preview voice to your voice library.
get_agent
Retrieve the configuration for a specific conversational agent.
get_voice
Fetch detailed metadata for a specific voice by its ID.
isolate_audio
Remove background noise and isolate speech from an audio file.
list_agents
List the conversational AI agents in your workspace.
list_conversations
List an agent's conversations with filtering and paging.
list_models
List available text-to-speech models and their languages.
make_outbound_call
Place an outbound phone call using an agent via Twilio or SIP.
search_voice_library
Search the shared ElevenLabs community voice library.
search_voices
Search your ElevenLabs library for voices by name or category.
speech_to_speech
Convert audio from one voice into another via voice conversion.
speech_to_text
Transcribe an audio file with optional speaker diarization.
text_to_sound_effects
Generate a sound effect from a text description and duration.
text_to_speech
Convert text to natural speech using a chosen voice and model.
text_to_voice
Generate three preview voices from a text voice description.
video_to_music
Generate background music tailored to one or more videos.
voice_clone
Create an instant voice clone from provided audio samples.