salutespeech-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SALUTE_AUTH_KEY | No | Legacy alias for SALUTESPEECH_API_KEY, same Base64 format | |
| SALUTESPEECH_API_KEY | No | Base64-encoded client_id:client_secret for SaluteSpeech API | |
| SALUTE_SPEECH_CLIENT_ID | No | Raw client ID for SaluteSpeech API (used with SALUTE_SPEECH_CLIENT_SECRET) | |
| SALUTE_SPEECH_CLIENT_SECRET | No | Raw client secret for SaluteSpeech API (used with SALUTE_SPEECH_CLIENT_ID) |
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| recognize_speechB | Speech recognition via SaluteSpeech. Accepts Base64 audio, returns text transcription. |
| synthesize_speechA | Text-to-speech via SaluteSpeech. Accepts text, returns Base64-encoded audio. |
| list_modelsA | List available SaluteSpeech models and voices for recognition and synthesis. |
| get_task_statusA | Check status of an async SaluteSpeech recognition task by ID. |
| recognize_fileA | Recognize speech from a local audio file. Auto-detects format from extension. |
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 5 tools
recognize_speech and recognize_file both perform speech recognition but differ by input source (Base64 vs local file), which is distinguishable. The other tools (get_task_status, list_models, synthesize_speech) have clearly distinct purposes.
All tool names follow a consistent verb_noun snake_case pattern: recognize_*, get_*, list_*, synthesize_*. No mixed conventions or vague verbs.
Five tools is well-scoped for a speech API covering recognition, synthesis, model listing, and async task management. Each tool earns its place.
The core speech recognition and synthesis workflows are covered, including async task status. Minor gaps include no explicit cancel/delete task operation, but the essential lifecycle is present.