voice-summary
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| VOICE_NAME | No | Voz concreta. Para edge, por ejemplo es-ES-AlvaroNeural. Para sapi5, por defecto es-es. | |
| VOICE_RATE | No | Velocidad de lectura. Acepta notación absoluta (escala SAPI5, 100 es normal) y relativa (por ejemplo +10%, -15%). | 100 |
| VOICE_ENGINE | No | Motor de síntesis. Valores: edge o sapi5. | sapi5 |
| VOICE_PLAYER | No | Reproductor de MP3 forzado. Ruta o nombre del reproductor. Por defecto se autodetecta. | |
| VOICE_VOLUME | No | Volumen. Acepta notación absoluta (100 es normal) y relativa (por ejemplo +10%, -15%). | 100 |
| MAX_SUMMARY_WORDS | No | Tope de seguridad de palabras por resumen. 0 = sin recorte. | 400 |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| speak_summaryA | Reads a summary out loud. Match its length to the work done: one short sentence for a small change, a fuller summary for a large task. First person, no literal code, no credentials or personal data. |
| list_voicesB | Shows the language, gender and voice in use, and the alternatives for the current language. For the full edge-tts catalog, run: python -m edge_tts --list-voices |
| set_languageA | Changes the voice language and gender, for when the user asks to speak another language or use a different voice. language: ISO code ("es", "en", "pt-BR"), "system" to follow the OS, or "auto" to detect it per summary. Empty keeps the current one. gender: "f"/"m", or "any" to follow the language default. Empty keeps the current one. |
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 3 tools
Each tool has a distinct purpose: set_language configures voice settings, speak_summary performs the core action, and list_voices provides introspection. There is no overlap; an agent can easily select the right tool.
All tool names use snake_case with a clear verb_noun pattern: set_language, speak_summary, list_voices. This is consistent and predictable.
With only 3 tools, the server is tightly scoped to its purpose: configure voice, speak summary, and inspect options. Each tool is necessary and there is no bloat.
The core lifecycle is covered: configure language/gender, speak a summary, and list voices. However, list_voices defers to an external command for the full catalog and there is no explicit stop/cancel operation, leaving minor gaps.