"Google Cloud Composer" matching MCP servers:

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.

Provides on-device Chinese speech recognition with traditional Chinese (Taiwan) output via MCP server, HTTP API, and CLI, ensuring privacy by processing audio locally without uploading to cloud services.

Enables local text-to-speech synthesis for Claude and Cursor using Supertonic 3, with support for multiple voices, expressions, and languages. No API key or cloud required.

A Windows-native MCP server that lets Claude Desktop transcribe audio files locally using whisper.cpp, with no internet connection required.

Enables text-to-speech conversion using Google Translate's TTS, supporting many languages and accents, and saving MP3 files.

Enables voice control of a Fujitsu heat pump through the FGLair cloud, exposing tools to read status and to propose and confirm changes to power, mode, temperature, and fan.

Enables AI assistants to transcribe links (YouTube, Google Drive, Dropbox), list and search your recordings for spoken words and moments, and read transcripts in json/txt/srt/vtt, summaries and metadata. It also lets them request new summaries and delete recordings, all through your own account with API-key or OAuth sign-in.

Enables transcription, summarization, and action item extraction from audio files on your Mac using MacWhisper and Claude Desktop, all locally without any cloud APIs.

Enables MCP clients to transcribe audio/video files locally, generate SRT subtitles, and burn captions into videos via tool calls, without a cloud API.

Automatically transcribes Google Chat voice messages using Groq Whisper API, and also supports local audio file transcription.

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

Provides multimedia understanding tools for LLM agents, enabling image, video, audio analysis and speech transcription via cloud-based MiMo V2.5 through OpenAI-compatible endpoints.

Enables Google Antigravity IDE to invoke local Windows Text-to-Speech tools for speaking text, listing available voices, and adjusting voice, rate, and volume via MCP.

Local-only transcription server for MCP agents, powered by CrispASR. Transcribes audio/video files without cloud uploads, supporting English and Chinese.

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 users to extract transcripts from Douyin videos, parse video metadata, retrieve download links, and transcribe audio files, using HTTP parsing with Chrome/Edge fallback and SiliconFlow cloud ASR by default.

This MCP server enables local-first video subtitle processing on Windows, offering tools for transcription, subtitle formatting, SRT/ASS export, FFmpeg rendering, and Kdenlive project creation without cloud APIs.

A stdio MCP server that enables long-form audio transcription through the NAVER Cloud CLOVA Speech API, accepting local files, trusted HTTPS URLs, or Object Storage keys with optional speaker diarization. It supports synchronous results and billable asynchronous jobs, letting clients check job status and retrieve transcripts with speaker labels and word timings alongside an offline health tool.

Know what your cloud agents did without reading logs. Heard MCP lets Claude, ChatGPT, Devin, Copilot and other cloud agents brief you out loud on your Mac, by name: what they got done, what's blocking them, or the decision they need. "Scout finished: the CI fix is merged." Answer out loud and the agent picks up your reply and keeps going. Hosted, OAuth sign-in, nothing to install.

MCP server for Chamade — a voice and chat gateway that lets your AI agent join meetings and DMs on Discord, Microsoft Teams, Google Meet, Telegram, SIP, Zoom, Nextcloud Talk, Slack, and WhatsApp.

Transcribe public videos and audio (YouTube, TikTok, Instagram, Facebook, Pinterest, Google Drive) into accurate, timestamped text from Claude, ChatGPT, Cursor or any MCP client. Spanish, English and dozens of languages auto-detected. Poll-based (transcription takes minutes), same free-beta limits as the app. Docs: https://justtranscribe.ai/mcp

Enables driving a Claude Code session directly from WhatsApp over a linked device or the official Cloud API, with bidirectional messaging, media attachments, local voice transcription, per-group personalities, and context recovery after restarts. Adds pairing-code access control, allowlists and group policies, plus remote approval or denial of tool permission prompts via emoji reactions — no API keys, no Docker.

A self-contained daemon that watches a directory, transcribes anything that lands in it, and presents the results to any AI agent through a standard protocol — no cloud, no subscriptions, no vendor lock-in.

MCP server that turns video URLs into transcripts and important keyframes locally, with no cloud or API keys.

Remote MCP server that exposes Google Gemini's text, image, video (Veo), and audio transcription capabilities as tools any MCP client can call directly.

Enables control of MentraOS smart glasses through tools for managing text displays, audio output, and input transcriptions. It integrates with Mentra Cloud to facilitate seamless interaction with smart glass hardware using natural language commands.

Enables an AI agent to read and send real iMessages—including text, voice notes, stickers, links, images, and reactions—through a managed cloud phone line without needing a Mac.

Local MCP server that enables voice input to Claude by transcribing microphone audio locally using faster-whisper, avoiding cloud services.

Enables converting text to speech audio in 20+ languages, returning base64-encoded MP3 output via Google TTS with x402 micropayment-based pay-per-call access.

Records your calls on your own computer, transcribes them on the machine, and lets an agent start, follow, question and annotate a call while it runs. No meeting bot, no account and no cloud; the same core runs as a self-hosted transcription server.

Lets an AI coding session send and receive WhatsApp messages, media, and transcribed voice notes from a linked personal number or the official Cloud API, with pairing codes and allowlists gating every inbound chat and tool approvals handled by emoji reaction.

A stdio MCP server that lets Claude Code sessions be driven directly from WhatsApp chats, with bidirectional messaging and media, voice-note transcription, pairing-code access control, per-group personalities, and emoji-reaction approval of tool requests. It supports both linked-device pairing for personal numbers and the official WhatsApp Cloud API for business DMs, and can also be run by other MCP clients on a poll-based basis.

Enables driving a Claude Code (or other MCP client) session directly from WhatsApp chats, with bidirectional messaging, media and locally transcribed voice notes, polls, per-group personalities, cron tasks, and emoji-reaction approval of tool requests. Inbound traffic is gated by pairing codes, allowlists, and per-group policies, and it runs either through a linked personal-device account or Meta's official Cloud API for business DMs.

Enables Claude Code sessions to be driven from WhatsApp, with bidirectional messaging, media and voice-note transcription, per-group personalities, and tool-permission approval via emoji reactions. Access is gated by pairing codes and allowlists, and it runs as a plain stdio MCP server using either a linked-device pairing or the official Cloud API.

A self-hosted MCP server over Streamable HTTP that lets a voice assistant query production records, capture persistent shift handovers, and run container-load calculations against synthetic factory data. It enables plant managers and line operators to inspect and update shift state through natural language without any cloud dependency.

Local voice toolkit over MCP: transcribe audio to text in 25 languages, synthesize speech in 9, and list available voices and languages. Runs fully on-device — no API keys, no cloud.

Profile-driven MCP server for Google Cloud Text-to-Speech that exposes tools to synthesize text to speech, run diagnostics, and stop playback, with voice and settings locked per profile.

Enables parsing Douyin video information, downloading videos without watermark, and transcribing speech to text using Tencent Cloud ASR.

Enables Claude to fetch YouTube video transcripts, using existing subtitles first and falling back to OpenAI Whisper transcription of the audio, with optional saving as Markdown files into a vault folder. It can run locally over stdio, be reached via an authenticated HTTP endpoint, or be exposed to claude.ai as a cloud connector backed by a local worker that does the actual fetching.

Turns a Claude Code session into a two-way WhatsApp endpoint, letting users send and receive messages, media, and voice notes from chat while strangers are blocked by pairing codes and allowlists, and tool-permission prompts are approved or denied by emoji reaction. It connects either through a linked personal device by default or an official business Cloud API, with per-group personalities and scheduled cron tasks.