"A tool for generating and live previewing Mermaid diagrams from code" matching MCP servers:

Exposes a local, hands-free voice room to any MCP client, letting agents read speaker-labelled conversation turns, wait for the next turn, list who is present, and speak aloud through local text-to-speech. Speech recognition, speaker identification and voice output all run on the user's own machine, so agents receive text with speaker names rather than audio.

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

Real-time English ↔ Mandarin Chinese speech translation for Claude. Transcribes audio locally with Whisper, translates via Claude API, and synthesises speech locally with Piper TTS. Pass a WAV file path. Claude handles the rest.

Provides live meeting context to an AI assistant during Google Meet or Zoom calls, enabling real-time transcript reading, decision tracking, and actionable advice in a side panel.

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.

Provides translation and language detection tools to AI agents, processing text, audio, and Google Meet recordings with emotional voice style preservation via Google's Gemini Live API.

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

MCP server for transcribing audio and generating structured customer requirement meeting minutes (including flowcharts) using Whisper and AI backends, with export to md/html/pdf/docx and model/settings management.

Enables AI agents to synthesize and play short summaries aloud while keeping full answers on screen, with queued speech and stop control using online natural voices or offline synthesis.

Lets any MCP-capable AI client create and manage AI voice agents without writing HTTP code.

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 that brings ElevenLabs to Claude Code — text-to-speech, sound effects, music generation, voice cloning, speech-to-speech, transcription, and voice isolation. 8 tools for industry-leading AI audio.

Enables local, offline, CPU-only transcription of video/audio into timestamped SRT subtitles with Whisper, Chinese TTS dubbing (including multi-speaker dialogue), and synthesis of a new dubbed video in a single command. Supports dubbing silent videos, translating and re-voicing foreign-language videos, and batch-adding narration to short clips within AI workflows.

Enables agents to synthesize Chinese speech with Edge-TTS or offline Piper and generate engine-level timestamp SRT subtitles, including batch parallel synthesis and voice presets.

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 AI clients to watch and hear videos from local files or YouTube, Vimeo, and Loom links by returning timestamped key frames, a transcript, a contact sheet, and a combined timeline, with all processing done locally.

Transcribe audio/video files using Groq-hosted Whisper with word-level timestamps, automatic caching, and cost estimation, offering up to 9x savings over OpenAI Whisper.

MCP server that provides a transcribe_audio tool to convert voice messages from channels into text using OpenAI Whisper, enabling Claude Code to process audio attachments.

Let your AI agent call your phone and talk to you — MCP servers for live, interruptible voice calls + tiered alerts, using free self-hosted pieces (pjsua2 + whisper.cpp + Linphone). No paid telephony, no extra API key.

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.

Manage voice AI agents from Claude Code, Cursor, VS Code, or any MCP-compatible assistant.

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.

Enables generating images, video, audio, and speech from MCP clients using your own Vidofy account, with access to hundreds of models for text-to-video, image-to-video, image editing, lipsync, text-to-speech, and voice cloning.

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 generate spoken audio locally on a GPU via the Chatterbox models, with zero-shot voice cloning from reference clips, multilingual output, and sentence-aligned chunking for long text.

MCP server for Whipscribe — transcribe audio and video from a URL or local file via Claude Desktop, Claude Code, Cursor, Windsurf, or any MCP-compatible client.

Enables MCP clients such as Claude Code, Cursor, and VS Code to generate speech through three MiMo TTS models: nine built-in voices (with singing and style/audio tags), voices designed purely from a text description, and voices cloned from a local mp3/wav sample. Audio is streamed and written only inside a sandboxed output directory, with non-overwriting filenames.

Enables any MCP client to start, poll, and stop microphone recordings from within a conversation, returning the accumulating transcript on demand. All transcription runs locally on-device, so no audio leaves the machine.

Enables text-to-speech synthesis through a streaming, GPU-accelerated gateway, exposing a single tool that returns playable WAV audio with configurable voice and speed.