FlowSpeech MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FLOWSPEECH_OUTPUT_DIR | No | Directory to save generated audio files | ~/.flowspeech-mcp/audio |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| flowspeech_ttsA | Generate a WAV recording with FlowSpeech. Requires a caller-known request UUID, an API key and paid API access; consumes account credits. |
| flowspeech_tts_multiA | Generate a two-speaker WAV recording with a caller-known request UUID. Each turn starts with Speaker1: or Speaker2:. Consumes account credits. |
| flowspeech_list_voicesC | Retrieve the current voice catalog from FlowSpeech. |
| flowspeech_quotaA | Read available, remaining and reserved API credits. |
| flowspeech_get_jobA | Read an existing job by job UUID or caller-known request UUID without creating a recording. Supply exactly one ID. |
| flowspeech_new_request_idA | Generate a fresh request UUID locally, without network access or an API key. Keep it before starting one recording. |
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 6 tools
Each tool has a clearly distinct role: single-speaker TTS, two-speaker TTS, voice catalog, quota, job lookup, and local request-ID generation. The main potential overlap between tts and tts_multi is resolved by descriptions specifying single- versus two-speaker output.
All tools share the flowspeech_ prefix and lowercase snake_case, making them predictable. The only minor inconsistency is that some names are verb-led (list_voices, get_job) while others are noun/acronym-led (tts, quota, new_request_id).
Six tools is well-scoped for a focused TTS API surface. Each tool appears to serve a distinct necessary purpose without obvious redundancy.
The surface covers the core workflow: request-ID creation, single- and multi-speaker synthesis, voice discovery, quota checking, and job status lookup. Minor gaps may exist around job listing/cancellation or explicit audio retrieval, but the essential lifecycle is represented.