Drizz Voice Generator
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ELEVENLABS_API_KEY | Yes | Your ElevenLabs API key | |
| ELEVENLABS_OUTPUT_DIR | No | Directory where MP3 files are saved (default: ~/Desktop) | ~/Desktop |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| text_to_speechB | Convert text to speech using ElevenLabs and save as MP3. Automatically enhances text with natural pauses and breathing room. Use presets for quick voice tuning: natural (default), conversational (YouTube/demos), narration (tutorials), dramatic (trailers). |
| batch_text_to_speechA | Convert multiple texts to speech in parallel. Each item can have a different voice and filename. Supports presets and auto text enhancement. |
| list_voicesA | List all available ElevenLabs voices |
| get_voice_idA | Look up an ElevenLabs voice ID by name |
| preview_text_enhancementA | Preview how text will be enhanced with SSML pauses and number expansion before sending to ElevenLabs. Use this to check and tweak scripts without burning API credits. |
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 5 tools
Each tool has a distinct purpose: single text-to-speech conversion, listing voices, looking up voice IDs, batch conversion, and previewing text enhancement. No overlap or ambiguity.
All tool names follow a consistent snake_case verb_noun pattern (e.g., text_to_speech, list_voices, get_voice_id, batch_text_to_speech, preview_text_enhancement). The naming is uniform and predictable.
Five tools is well-scoped for a voice generator server, covering single and batch conversion, voice management, and a preview utility without unnecessary bloat.
The tool surface covers the full generation workflow: text enhancement preview, single/batch generation, and voice lookup. No obvious missing operations for the stated purpose.