mcp-tts
Active·★ 74·MIT·Updated 2026-10-19
`mcp-tts` is an MCP server that integrates various Text-to-Speech providers, including local macOS `say` and cloud APIs like ElevenLabs, Google TTS, and OpenAI TTS, into AI agent environments. It enables AI agents within tools like Claude Desktop and Cursor IDE to verbalize plans, summaries, and alerts, enhancing interactive communication.
#Text-to-Speech#TTS#MCP Protocol#AI Agent Tooling#Speech Synthesis#Go#API Integration#Voice AI
01
Features
01Integrates multiple TTS providers: macOS `say`, Voice (local Qwen3-TTS), ElevenLabs, Google TTS, and OpenAI TTS.
02Supports the Model Context Protocol (MCP) for seamless integration with AI agent platforms like Claude Desktop, Claude Code, Codex CLI, and Gemini CLI.
03Offers configuration for sequential or concurrent speech playback, suppression of "Speaking:" output, and saving audio to disk.
04Includes a `speak` skill for automatic vocalization of agent plans, issue resolutions, summaries, and state changes.
05Provides options for various voices, quality models, speed control, and custom voice instructions for cloud TTS providers.
02
Compatibility
Go
Runtime
Verified via docs
macOS
Operating System
Verified via docs
Claude Desktop
Integration Platform
Verified via docs
Claude Code
Integration Platform
Verified via docs
Codex CLI
Integration Platform
Verified via docs
Gemini CLI
Integration Platform
Verified via docs
03
Quick start
1
$ go install github.com/blacktop/mcp-tts@latest
04
Use cases
↳Add Text-to-Speech capabilities to AI agent development environments (e.g., Claude Desktop, Cursor IDE) for interactive feedback.
↳Automatically vocalize AI agent outputs such as finalized plans, resolved issues, and task summaries.
↳Alert users audibly when long-running operations change state or when human intervention is required.
↳Utilize local-only TTS (macOS `say`, Voice) for privacy-sensitive applications or environments without internet access.
↳Enhance accessibility and user experience by providing auditory feedback from AI tools.
05
Alternatives
voice-ai★ 748
Rapida is an open-source, end-to-end voice AI orchestration platform for building real-time conversational voice agents with audio streaming, STT, TTS, VAD, multi-channel integration, agent state management, and observability.
NornicDB★ 917
NornicDB is a high-performance graph + vector database built for AI agents and knowledge systems. It speaks Neo4j's (Bolt + Cypher) and qdrant's (gRPC) languages so you can use Nornic with zero code changes, while adding intelligent features including a graphql endpoint, air-gapped embeddings, GPU accelerated search, and other intelligent features.
Comments
Log in to leave a comment
No comments yet. Be the first!