agents-voice
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 | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| voice_speakA | Speak a short, natural voice summary (1-2 sentences) directly to the user's ears. Use this tool at the end of substantive turns to tell the user what was done, without reading code, diffs, or markdown formatting. Keep it concise, natural, and friendly. Args: message: The concise spoken text (e.g. 'Hab den Bug gefixt und Tests sind grün.'). provider: Optional override ('openrouter', 'openai', 'gemini', 'elevenlabs', 'azure', 'custom'). model: Optional model override (e.g. 'openai/gpt-4o-mini-tts', 'elevenlabs/eleven-v4-turbo'). voice: Optional voice override (e.g. 'marin', 'cedar', 'Kore', 'de-DE-Seraphina:DragonHDLatestNeural'). |
| voice_stopA | Immediately stops any currently playing speech audio if the user requests silence. |
| voice_play_latestA | Plays the most recent speech summary stored in the voice inbox. |
| voice_statusA | Checks the status of the voice output system, active provider, configured keys, and bridge. |
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
The tools are mostly clearly distinct: speak emits new speech, stop halts playback, status reports system state, and play_latest replays the latest stored summary. The only mild ambiguity is between voice_speak and voice_play_latest, since both result in spoken audio, but their descriptions distinguish creation from replay.
All tools use a consistent snake_case voice_verb pattern: voice_play_latest, voice_speak, voice_status, voice_stop. The shared prefix and predictable verb style make the surface easy to scan.
Four tools is well-scoped for a voice-output helper: speak, replay latest, check status, and stop. Each tool has a clear purpose and none feels superfluous.
The set covers the core lifecycle: producing speech, replaying the latest summary, checking provider/status, and stopping playback. Minor gaps like pause/resume or listing voice history are not essential for the apparent agent workflow.