ElevenLabs Voice-to-Voice Agent
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LLM_PROVIDER | No | LLM provider: 'anthropic' (default) or 'openai' | anthropic |
| OPENAI_API_KEY | No | OpenAI API key (required if using OpenAI) | |
| ANTHROPIC_API_KEY | No | Anthropic API key (required if using Anthropic) | |
| ELEVENLABS_API_KEY | Yes | ElevenLabs API key (required) | |
| ELEVENLABS_OUTPUT_DIR | No | Directory for output MP3 files (defaults to current working directory) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_voicesA | List all voices available in ElevenLabs. Returns voice IDs, names, and labels. |
| get_voiceA | Get detailed information about a specific ElevenLabs voice by its ID. |
| list_modelsA | List all available ElevenLabs TTS models with their capabilities and supported languages. |
| text_to_speechA | Convert text to speech using ElevenLabs. Saves the audio as an MP3 file and returns the file path. |
| speech_to_textA | Transcribe an audio file to text using ElevenLabs Speech-to-Text (scribe_v1). Supports WAV, MP3, and other common formats. |
| get_user_infoA | Get the current ElevenLabs user/subscription info including character usage and limits. |
| get_historyB | Retrieve the history of TTS generations from ElevenLabs. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| voice_agent_persona | Create a voice AI agent with a specific persona. The agent picks a matching ElevenLabs voice and speaks every response aloud via text_to_speech. |
| start_voice_session | Initialize a live voice conversation. The agent listens via speech_to_text and responds aloud via text_to_speech in a continuous loop. |
| find_voice_for_role | Analyze available voices and recommend the best matches for a specific use case, with audio samples for each. |
| voice_showcase | Render the same phrase in multiple different ElevenLabs voices for side-by-side comparison. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| voices | Live list of all ElevenLabs voices with IDs, categories, and labels. Read this before calling text_to_speech to pick the right voice. |
| models | Available ElevenLabs TTS and STT models with capabilities and supported languages. |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Begwen/Agentic-Voice-AI-System---MCP-Native-'
If you have feedback or need assistance with the MCP directory API, please join our Discord server