"A search about the concept and practice of magic" matching MCP servers:

Self-host a realtime voice-call companion for coding agents. Exposes an MCP endpoint that agents can poll as an alternate input stream.

Enables voice assistants to find nearby service providers, connect users to live video representatives for natural conversation, and handle appointment booking. It also returns confirmed bookings so the assistant can add them to its calendar.

Enables AI assistants to download YouTube videos and transcribe them locally using OpenAI's Whisper speech recognition model.

Enables MCP-capable chat clients to synthesize speech from text, convert it with a local RVC voice model, and render the result in an inline audio player.

MCP server for a Polish language tutor that provides interactive exercises, concept explanations, pronunciation practice, and progress tracking using a local LLM and a knowledge graph.

A self-hosted MCP server that connects AI clients to local media-generation backends like ComfyUI and Blender, and provides built-in utilities for video/audio analysis, editing, subtitles, speech, and scene detection via a persistent file cache.

Enables hair colourists to capture a client's colour formula by voice, retrieve it on the next visit, and scale the mix to today's bowl, with per-client memory and clarification when names are ambiguous.

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

Enables MCP clients such as Claude Code, Codex and Cursor to retrieve timestamped transcripts of public YouTube videos, either from cache, from native captions, or via asynchronous audio-generation jobs that are polled by job ID. It returns the source URL, selected language and millisecond-offset segments without summarizing the video itself.

Local MCP voice coach that provides English pronunciation, grammar, and fluency feedback from microphone recordings. It supports free-form voice conversation, focused practice drills, phoneme-level feedback, prosody hints, and learner-profile guidance.

Enables Claude Code to place real outbound phone calls to a user when a session is blocked, capture their spoken decision, and resume the session.

Voice input for Claude Code — speak Vietnamese or English; hold a hotkey, speak, release, and the transcribed text is cleaned and pasted into the input box for editing before sending.

Enables AI agents to interact with the ParrotScribe transcription service on macOS, providing tools to start/stop transcription, retrieve real-time and historical transcripts, and search across sessions.

Enables an assistant to transcribe video or podcast recordings, then read, search, summarize, and manage the resulting transcripts through MCP tools.

Enables real-time transcription and heuristic vocal stress analysis of live financial webcasts, providing an LLM with rolling transcripts and a stress score.

Lets AI assistants query available voices from an OpenAI-compatible TTS service and synthesize text into audio with a chosen voice, tone, and speed, returning a public audio URL instead of Base64 data.

Enables spoken consulting case interview practice through Claude, providing real-time cases, grading on structure, analytics, judgment, and communication, and targeted practice drills.

Enables local, on-device transcription of local files or URLs, returning a job ID and making transcripts, segments, and full-text search available as processing completes. Uses Whisper large-v3 with SQLite storage and stdio transport, so audio and video never leave the machine.

Local-first CLI + MCP server for meeting recordings - Whisper transcription,

Enables Claude to fetch the spoken text of YouTube videos from any URL or video ID, listing available captions and languages and paging through long transcripts. It also handles proxy configuration to work around YouTube IP blocks.

Turns Claude or ChatGPT into a live system design interviewer that watches a hand-drawn whiteboard, reads the diagram as structured data or an image, hears spoken answers, pins questions on components, and grades the session. Everything runs locally, so users can practice mock interviews on their own machine without API keys.

Enables TOEIC speaking sentence practice with adaptive quizzes, voice input, and instant feedback through keyword matching and mastery scoring.

Enables AI agents on macOS to securely read and search the local Messages database, catch up on missed messages via a persistent inbox, and send texts or files to allowlisted chats, with optional voice note transcription and text-to-speech.

MCP server for the AssemblyAI API, providing tools for transcription, subtitles, speaker turns, word search, and LeMUR-based queries.

Connects to the TypeWhisper macOS app to let coding agents transcribe local files, inspect model status, search history, and manage dictionary terms and corrections.

A Node.js server that enables AI assistants to interact with Bouyomi-chan's text-to-speech functionality through Model Context Protocol (MCP), allowing for voice reading of text with adjustable parameters.

Enables AI assistants to place and steer real phone calls through ElevenLabs voice agents: draft a briefing with the number, language, goal and permitted facts, rehearse it in text, confirm to dial, then follow progress, answer the agent's questions mid-call, and retrieve the transcript, duration and cost. Includes guardrails such as a fixed AI disclosure line, per-person call and minute limits, number restrictions and retention-based deletion of calls and transcripts.

A MCP server that enables transcription of audio files using OpenAI's Speech-to-Text API, with support for multiple languages and file saving options.

A server that enables Claude 3.7 and other AI agents to access VOICEVOX-compatible speech synthesis engines (AivisSpeech, VOICEVOX, COEIROINK) through the Model Context Protocol.

Best VoiceAI White Label Platform for Agencies with Full MCP Connectivity to Any Platform for Custom VoiceAi & AI Chat Integrations and You Keep 100% of the Profits