speaches-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| STT_MODEL | No | Default speech-to-text model | Systran/faster-whisper-large-v3 |
| TTS_MODEL | No | Default text-to-speech model | speaches-ai/Kokoro-82M-v1.0-ONNX |
| TTS_VOICE | No | Default TTS voice | af_heart |
| SPEACHES_URL | No | Base URL of your speaches instance | http://speaches:8000 |
| OPENAI_API_KEY | No | Required by the OpenAI SDK but not used by speaches | dummy |
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 |
|---|---|
| transcribe_audioD | – |
| text_to_speechD | – |
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 2 tools
The two tools have clearly distinct purposes: text_to_speech converts text to audio, and transcribe_audio converts audio to text. There is no overlap.
Both tool names follow a consistent verb_noun pattern using underscores, making them predictable and easy to understand.
With only two tools, the server feels thin for a speech processing domain, where additional tools for voice management or language selection might be expected.
The core operations of text-to-speech and transcription are covered, but missing features like voice listing or parameter configuration create minor gaps.