io.github.Engr-FaizanAli/text-to-speech
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CODEX_TTS_BACKEND | No | Legacy environment variable for TTS backend. | sapi |
| TEXT_TO_SPEECH_BACKEND | No | Backend for text-to-speech. Options: sapi, piper, transformers_mms, http. | sapi |
| TEXT_TO_SPEECH_KEEP_AUDIO | No | If set to true, temporary WAV files are not deleted after playback. | false |
| CODEX_TTS_FALLBACK_BACKEND | No | Legacy environment variable for fallback TTS backend. |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| speak_textA | Read text aloud locally and return after playback finishes. |
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 1 tool
Only one tool exists, so there is no possibility of confusion between tools. The purpose of speak_text is singular and clear.
The single tool name follows a clear verb_noun pattern ('speak' + 'text'), which is consistent and intuitive. With only one tool, there are no mixed conventions.
The server has exactly one tool, which feels thin for a text-to-speech service. While it covers the core action, users might expect additional tools for voice configuration or listing available options.
The tool provides the fundamental speak action but lacks obvious capabilities like voice selection, speed adjustment, or cancellation. This leaves notable gaps for a complete TTS workflow.