Speech AI - Pronunciation, STT & TTS

Each tool has a clearly distinct purpose with no ambiguity. The assessment, transcription, synthesis, and service health tools target different aspects of speech AI (pronunciation scoring, STT, TTS, diagnostics, and metadata). Even the two transcription tools are clearly differentiated: one for basic English transcription and another for advanced multilingual Whisper transcription with diarization.

Tool names follow a highly consistent verb_noun pattern throughout. All tools use snake_case with clear action prefixes (assess_, check_, get_, list_, synthesize_, transcribe_) followed by specific nouns. This predictable naming makes it easy for agents to understand each tool's function at a glance.

With 10 tools, this server is well-scoped for its speech AI domain. Each tool earns its place by covering distinct functionalities: pronunciation assessment, transcription (basic and pro), speech synthesis, service health checks, and metadata retrieval. The count is neither too sparse nor overwhelming for the comprehensive speech processing scope.

The tool surface provides complete coverage for speech AI workflows. It includes core operations (pronunciation assessment, transcription, synthesis), diagnostic tools (service health checks), and metadata access (phoneme inventory, voice list). There are no obvious gaps—agents can perform end-to-end speech processing tasks without encountering dead ends.