ElevenLabs
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ELEVENLABS_API_KEY | Yes | ElevenLabs API key | |
| ELEVENLABS_TIMEOUT | No | API timeout in ms | 120000 |
| ELEVENLABS_OUTPUT_DIR | No | Directory for auto-saved audio | ./generated-media |
| ELEVENLABS_DEFAULT_VOICE | No | Default voice name for TTS | Rachel |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| text_to_speechB | Convert text to natural speech using ElevenLabs' industry-leading TTS. Saves audio file to disk. Trigger: 'elevenlabs tts', 'elevenlabs speak', or 'elevenlabs text to speech'. |
| sound_effectsA | Generate sound effects from text descriptions using ElevenLabs. Great for game audio, video production, and creative projects. Trigger: 'elevenlabs sfx', 'elevenlabs sound effect', or 'elevenlabs generate sound'. |
| generate_musicC | Generate studio-grade music from text descriptions using ElevenLabs. Trigger: 'elevenlabs music', 'elevenlabs generate music', or 'elevenlabs compose'. |
| list_voicesA | List and search available ElevenLabs voices. Trigger: 'elevenlabs voices', 'elevenlabs list voices', or 'show elevenlabs voices'. |
| clone_voiceA | Create an instant voice clone from audio samples. Requires 1-2 minutes of clear audio. Trigger: 'elevenlabs clone', 'elevenlabs clone voice', or 'elevenlabs create voice'. |
| speech_to_speechB | Transform audio to use a different voice while preserving emotion and cadence. Trigger: 'elevenlabs voice change', 'elevenlabs speech to speech', or 'elevenlabs sts'. |
| transcribeA | Transcribe audio to text using ElevenLabs Scribe with optional speaker diarization. Supports 90+ languages. Trigger: 'elevenlabs transcribe', 'elevenlabs stt', or 'elevenlabs speech to text'. |
| voice_isolationB | Isolate vocals from background noise in audio files. Great for cleaning up recordings. Trigger: 'elevenlabs isolate', 'elevenlabs voice isolation', or 'elevenlabs clean audio'. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 8 tools
Each tool has a unique and clearly distinct purpose: voice cloning, music generation, voice listing, sound effects, speech-to-speech, text-to-speech, transcription, and voice isolation. No two tools overlap in functionality.
All tool names follow a consistent snake_case verb_noun pattern (e.g., clone_voice, generate_music, text_to_speech). Even 'transcribe' is a verb and fits the pattern. No mixing of conventions.
With 8 tools, the set is well-scoped for an audio AI server. Each tool serves a distinct audio processing task without being overloaded or insufficient.
The tool set covers major audio workflows: generation (music, sound effects), conversion (TTS, speech-to-speech, clone), transcription, listing, and isolation. There are no obvious gaps for common use cases.