MCP Coqui TTS Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 |
|---|---|
| speakC | Convert text to speech using Coqui TTS |
| list_modelsA | List available TTS models |
| synthesize_long_textB | Synthesize longer text with automatic chunking |
| clone_voiceB | Clone a voice from an audio sample (requires XTTS model) |
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 4 tools
Most tools are clearly distinct: list_models, clone_voice, and speak/synthesize_long_text target different actions. The only ambiguity is between speak and synthesize_long_text, though the long-text description clarifies the boundary.
All names use snake_case and are readable. The pattern is mostly verb_noun (list_models, synthesize_long_text, clone_voice), with 'speak' as a minor bare-verb deviation.
Four tools is well-scoped for a focused TTS server: model listing, standard synthesis, long-text synthesis, and voice cloning. Each tool earns its place without redundancy.
The core TTS lifecycle is covered: discovering models, synthesizing speech (standard and long), and cloning voices. Minor gaps exist around voice management or output options, but agents can work around them.