In-depth architectural comparison of the Speech.sh and Claude Code Tts MCP servers. Compare execution transports, security boundaries, tool capabilities, quality scores, and ready-to-paste client installation snippets for Claude, Cursor, Windsurf, and VS Code.
At a Glance & Executive Verdict
Speech.sh
Text-to-Speech · Remote HTTP/SSE
Quality: 39/100 (Fair) | Auth: API Key required
Claude Code Tts
Text-to-Speech · Local stdio
Quality: 43/100 (Fair) | Auth: API Key required
Verdict Summary: Choose Speech.sh if you need specialized Text-to-Speech tools running via a hosted cloud SSE transport. Choose Claude Code Tts if your workspace requires Text-to-Speech integration with local subprocess execution. Both servers can be configured concurrently in your client's mcpServers manifest.
Which MCP Server Should You Choose?
Choose Speech.sh when:
You need dedicated capabilities in the Text-to-Speech domain.
You prefer remote streaming HTTP/SSE transport architecture.
Your security boundary fits: API Key required (BYOK (Pay Provider Direct)).
You have access to required keys: OPENAI_API_KEY, SPEECH_VOICE, SPEECH_SPEED, SPEECH_MODEL, SPEECH_API_URL.
Let the agent speak things out loud, notify you when he's done working with a quick summary
MCP server plugin for Claude Code that converts text to speech using OpenAI's TTS API. Features 6 voices, worker pool architecture, mutex-protected playback, and cross-platform support.
Speech.sh is categorized under Text-to-Speech and uses a remote streaming HTTP/SSE transport. In contrast, Claude Code Tts belongs to Text-to-Speech using local stdio subprocess. Select Speech.sh when you need capabilities focused on text-to-speech and Claude Code Tts when you require tools for text-to-speech.
Primary tools included: Integration with OpenAI TTS API (model tts-1), Six selectable voices: alloy, echo, fable, onyx, nova, shimmer, Worker pool architecture with queue for concurrent processing.