Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| EDGE_TTS_RATE | No | Default speed (-50% to +100%). | +0% |
| EDGE_TTS_PITCH | No | Default pitch (-50Hz to +50Hz). | +0Hz |
| EDGE_TTS_VOICE | No | Default voice name (e.g., uk-UA-OstapNeural, en-US-AriaNeural). | uk-UA-OstapNeural |
| EDGE_TTS_PLAYER | No | Audio player to use. Auto-detected by platform if set to 'auto'. Alternatives include ffplay, mpv, afplay, paplay. | auto |
| EDGE_TTS_VOLUME | No | Default volume (-50% to +100%). | +0% |
Capabilities
Features and capabilities supported by this server
| 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 | Speak text aloud using Microsoft Edge TTS.
Args:
text: Text to speak
voice: Voice name (e.g., en-US-AriaNeural, uk-UA-OstapNeural)
rate: Speech rate (-50% to +100%, e.g., +20%)
volume: Volume (-50% to +100%, e.g., +10%)
pitch: Pitch (-50Hz to +50Hz, e.g., +5Hz)
Returns:
Confirmation message |
| list_available_voices | List available TTS voices.
Args:
language: Filter by language code (e.g., en, ru, de). Empty for all.
Returns:
List of voices with their details |
| get_config | Get current TTS configuration.
Returns:
Current settings |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |