@runapi.ai/elevenlabs-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| RUNAPI_API_KEY | No | Your RunAPI API key. Can also be set in ~/.config/runapi/config.json |
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
} |
| logging | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| loginA | Authenticate RunAPI by opening a browser PKCE login flow and saving the API key to ~/.config/runapi/config.json. |
| isolate_audioC | Create a ElevenLabs task on RunAPI (isolate audio). Returns a task id, status, and output URLs. |
| speech_to_textB | Create a ElevenLabs task on RunAPI (speech to text). Returns a task id, status, and output URLs. |
| text_to_dialogueB | Create a ElevenLabs task on RunAPI (text to dialogue). Returns a task id, status, and output URLs. |
| text_to_soundC | Create a ElevenLabs task on RunAPI (text to sound). Returns a task id, status, and output URLs. |
| text_to_speechB | Create a ElevenLabs task on RunAPI (text to speech). Returns a task id, status, and output URLs. |
| get_taskB | Fetch the current status and latest result payload for a elevenlabs task. |
| check_pricingB | Look up RunAPI pricing for the elevenlabs model line. |
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
The create-task tools share identical boilerplate descriptions, and text_to_speech vs text_to_sound (speech vs sound effects) are easily confused without further detail. login, get_task, and check_pricing are clearly distinct, but the audio-generation cluster has fuzzy boundaries.
All names use consistent snake_case, and the *_to_* / verb_noun pattern is largely predictable. The lone bare verb 'login' is a minor deviation from the otherwise uniform resource-action style.
Eight tools is a well-scoped set for an audio task API covering generation, transcription, isolation, task polling, auth, and pricing. Each tool earns its place with no redundant entries.
Core generation and retrieval are covered, but the async task surface is incomplete: there is no list_tasks, cancel_task, or delete_task, which agents commonly need to manage submitted jobs. Voice/model enumeration is also absent.