"Speech & Transcription" matching MCP servers:

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

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 automated conversational phone calls using Asterisk with Speech-to-Speech capabilities, allowing users to make phone conversations as easily as writing a prompt.

Allows invoking Claude in Telegram chats via inline mentions or business bot, with context from chat history and media transcription.

Enables running Claude Code sessions from Telegram with group auto-join, voice transcription, reply-quote context, and a restart-proof polling daemon.

Enables AI assistants to have voice conversations and screen sharing capabilities via WebRTC, using Pipecat for speech-to-text and text-to-speech.

Connects WhatsApp to Claude Code, enabling message reading, audio transcription, image analysis, and message sending with full codebase context.

Fast MCP Telegram — Production-grade Telegram MCP server with direct MTProto API, multi-user ACL, dual transport (stdio + HTTP SSE), voice transcription, and context-optimized design. One-command setup with uvx fast-mcp-telegram

Provides text-to-speech and Telegram notification capabilities via the Model Context Protocol. Supports multiple TTS providers and Telegram messaging with optional setup web interface.

An MCP server that lets Claude read live transcripts and notes from Alt, a real-time lecture/meeting transcription app, while a recording is in progress, pulling only new lines each time.

Bridges AI assistants to a Telegram bot to enable two-way messaging, interactive confirmations, and live status updates. It supports automatic voice transcription via local Whisper models and provides secure, single-user communication for MCP-compatible hosts.

Exposes Bitrix24 REST API to AI assistants, enabling management of tasks, CRM entities, call recordings (with local transcription), users, workgroups, and Knowledge Base articles.

Enables comprehensive Google Meet and Calendar management through Google Calendar API v3 and Google Meet API v2, supporting calendar event creation with Meet links, space management, transcription, recording, attendance tracking, and meeting moderation controls.

This server enables AI models to send SMS messages and initiate Text-to-Speech calls programmatically using ClickSend's API with built-in rate limiting and input validation.

Local MCP server for agents to search, structure, and export authorized WhatsApp Web conversations. Uses Playwright for DOM interaction, supports message search, export, media transcription, and controlled message sending.

Connect AI agents to Wavix's communications platform to send SMS, make and manage voice calls, run 2FA flows, and access speech analytics, phone number management, and SIP infrastructure.

Open-source registry of structured API specs for African providers: payments (Wave, Paycard, ...), SMS and WhatsApp (Africa's Talking, Infobip, ...), identity, delivery and speech. AI agents read the real endpoints, parameters and gotchas and write the integration. Each capability is marked verified (tested against the live API) or ready (written from the docs, not yet tested).

Enables driving a Claude Code session from a linked personal WhatsApp account or an official Cloud API business number, with bidirectional messaging, full media and voice transcription, per-chat personalities, and context recovery after restarts. Inbound traffic is gated by pairing codes, allowlists and per-group policies, and tool-permission requests can be approved or denied remotely with an emoji reaction.

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.

Provides Claude Code read-only access to WhatsApp chats by mirroring them into a local SQLite database, allowing search, message listing, media retrieval, and optional voice-note transcription without any send capability.

Enables LLM applications to make voice calls and send SMS messages through the Vonage API, allowing AI assistants to perform real-world telephony operations with support for speech recognition and customizable voice parameters.

A QQ toolbox MCP server that lets an agent manage Qzone posts (publish, list, like, comment, delete, set visibility), friend feeds, visitors, confession-wall submissions and scheduled posts, while also editing the bot's profile (avatar, nickname, signature, online status, status lookup) via OneBot/SnowLuma. It additionally sends images and text-to-speech voice clips into private or group chats and manages tool whitelists.

Enables driving an AI coding session directly from WhatsApp over either a linked-device connection or the official Cloud API, with bidirectional messaging, media, polls, and local voice transcription. Access gating, per-group personalities, and emoji-based approval of tool requests keep strangers out and let users authorize or deny actions remotely.

Gives any text-based AI a voice and ears inside a Discord voice channel by transcribing speech, relaying to an LLM/agent, and speaking replies back.

Enables LLMs to make voice calls and send SMS messages through the Vonage API, allowing AI assistants to perform real-world telephony operations with support for speech recognition and multi-language conversations.

Enables Connectome agents to interact through Telegram Bot API chats, including text and rich messages, voice transcription, photos and albums, attachments, topics, reactions, action keyboards, and callback-based decisions.

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 a Claude Code session to send and receive WhatsApp messages through either a linked device or the official Cloud API, including media, voice-note transcription, polls, and per-group personalities. Inbound messages are gated by pairing codes and allowlists, and tool permission requests can be approved or denied remotely with an emoji reaction.

Enables users to drive a Claude Code session from chat messages on a linked phone number or an official business account, with bidirectional text and media, local voice-note transcription, per-chat personalities, pairing-code access control, and tool-approval by emoji reaction. It also supports polls, scheduled tasks, and context recovery after restarts for other stdio MCP clients.

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.