"Improving the Intelligence of Large Language Models" matching MCP servers:

A language expression coach MCP server that provides native-sounding translations with cultural context, tone notes, and audio pronunciation for over 13 languages.

Enables MCP agents to retrieve Japanese voice presets and synthesize anime-style speech, including reference-conditioned voice cloning, using the CPU of the computer running the local Gradio app.

Enables agents to convert text to speech using OpenAI's TTS models with voice selection, delivery instructions, and queue-based audio playback. Supports both blocking and non-blocking modes for flexible audio generation and playback control.

MCP server for MiniMax's multimodal generation models, enabling text-to-speech, voice cloning, image, video, and music creation through natural language.

macOS Notification MCP enables AI assistants to trigger native macOS sounds, visual notifications, and text-to-speech. Built for Claude and other AI models using the Model Context Protocol.

Voice interface for Claude Code enabling hands-free, conversational interaction entirely on-device for Apple Silicon Macs. It provides push-to-talk transcription and automatic spoken responses via local AI models.

Enables speech-to-text and text-to-speech conversion using OpenAI-compatible APIs. Supports customizable models, voices, and output directories.

Enables natural language generation of speech in any language, voice creation and management, music composition, dubbing, pronunciation dictionaries, and account history/usage through any MCP client using your own API key.

Enables AI models to generate high-quality voice messages from text using the Piper TTS engine, with automatic model management and audio streaming.

MCP server that exposes BytePlus Seed Audio 1.0 tools for generating natural speech and audio, checking task status, and listing voices/models.

Enables text-to-speech and speech-to-text through MCP tools, using Groq's free hosted endpoints when configured and falling back to fully local keyless models otherwise. Also provides voice listing and provider health checks.

Enables spoken conversations with Claude on a Mac: Claude speaks through speakers, listens to the user's natural replies, and transcribes them locally. No audio leaves the computer, and it includes tools for voice setup and a hands-free voice mode.

Voice interface for Claude Code: you talk, the agent listens, codes, and talks back while it works. Live speech-to-text with turn-taking, Grok/xAI voices with per-subagent personas, and a real-time HUD dashboard.

An MCP server that makes AI agents speak a brief summary of every response out loud using TTS.

Enables progress-triggered text-to-speech in Cursor Agent, with speak and stop controls and voice matching the system UI language.

Enables Claude to speak in 70+ languages, including pronunciation, audio flashcards, and full language lessons with tutor personas.

Enables AI models to speak and sing using retro-style formant speech synthesis, converting text or phoneme strings to WAV audio via MCP tools.

MCP server for the Supertone TTS API. Generate natural speech, browse and preview the voice catalog, predict synthesis cost, and create cloned voices — directly from Claude Desktop, Cursor, or any MCP-compatible client. Supports Korean, English, Japanese, and 20+ other languages, with speed, pitch, and emotion-style control.

Enables MCP clients to synthesize text into speech locally and play it through the machine's audio, with selectable voices and playback speed.

Image, video, chat and text-to-speech models (GPT Image, Gemini Image, Veo, Kling, Seedance, Claude, GPT, Gemini) behind one API key. generate_image returns a preview the model can see, and review_image has a vision model critique the result and propose a corrected prompt, so an assistant can generate, check and fix images on its own.