Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ELEVENLABS_STYLE | No | Value for styling of generated speech, default is 0.1. | 0.1 |
| ELEVENLABS_API_KEY | Yes | Your ElevenLabs API key required for accessing the text-to-speech service. | |
| ELEVENLABS_MODEL_ID | No | The model ID for ElevenLabs, default is 'eleven_flash_v2'. | eleven_flash_v2 |
| ELEVENLABS_VOICE_ID | Yes | The ID of the voice you wish to use for text-to-speech conversion. | |
| ELEVENLABS_STABILITY | No | Value representing the stability of the generated speech, default is 0.5. | 0.5 |
| ELEVENLABS_OUTPUT_DIR | No | Directory where output audio files will be stored, default is 'output'. | output |
| ELEVENLABS_SIMILARITY_BOOST | No | Value representing the similarity boost, default is 0.75. | 0.75 |
Schema
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |