- Conduid
- Marketplace
- #speech-to-text
MCP servers tagged speech-to-text
140 live MCP servers tagged "speech-to-text", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with speech-to-text.
Software Agent
A visible, governed, voice-enabled team of AI software agents working together in your terminal.
Stereo Reels Public
Agent skill that turns a long recording into short vertical clips, verifying every cut by transcribing it again.
Saybench
Benchmark the full voice-AI pipeline on your own audio — STT (batch + streaming), LLM TTFT, speech-to-speech, and TTS. WER by failure mode, keyterm recall, real-time-paced latency…
AI Translate
Cross-platform desktop app that translates documents, PDFs, subtitles, images, audio, and live speech into 40+ languages. Powered by LLMs (Gemini, OpenAI-compatible) with CLI and…
Vdl MCP
MCP server for vdl — lets Claude and other AI assistants resolve, download and transcribe (Whisper) videos via your self-hosted vdl instance
Meeting Summary Tool
Local-first, evidence-linked compiler for meetings and lectures.
Rant Mac
talk messy. write clean. — a native, local-first voice input system for macOS. Your keys, your Mac, your data. MIT.
DeepVid
Give AI the ability to watch videos. Enables Claude, Codex, and any AI agent to query videos via MCP. Auto-syncs illustrated notes to Obsidian with mindmaps and chapter skimming.…
TextWren
Translate, fix grammar and dictate in any macOS app. ⌘C twice for a popup, fn⌃ to talk; cloud models or fully on-device.
Podcast Transcriber
Transcribe any podcast episode — CLI + MCP server. Three tiers: Gemini (speakers + tone), OpenAI Whisper API, or free local Whisper. Works on Mac, Windows, Linux.
Psibot
Always-on AI agent for Telegram, powered by Claude Agent SDK. Runs 24/7 on your Mac with your Max subscription. $0 API costs. Multimodal: voice, images, YouTube, browser automatio…
Yell At AI
STT with emotions; Dictation that carries how you said it — a local, model-free prosody layer that hands your AI the emphasis, urgency and hesitation your transcript throws away.
Notables
Mac lecture recorder that transcribes on a Windows GPU and files Markdown notes with Claude
Adversaria
A meeting notetaker that runs entirely on your own machine. No bot joins the call, nothing is uploaded, and the recording is deleted once it's transcribed. macOS · MIT.
Openmy
Local-first personal context engine: turns your recordings and screen into memory your AI agents can use and you can correct.
Speakly
High-performance, extensible speech recognition toolkit for Rust — OpenAI Whisper, Google, ByteDance Doubao, local Whisper.cpp
Moanete
🎙️ AI meeting copilot — real-time transcription, LLM-powered insights, and Q&A as a browser app with PiP overlay
Vibecoding With Closed Eyes On Sofa
静默改代码，张嘴说人话 · Close your eyes, lean back, and let your AI agent code while you talk like a boss 🛋️
Sanctum
AI meeting notes that listen quietly and remember for your whole team: live transcripts, cited research, shared agent memory via MCP and SDKs.
Mitschnitt
Record any meeting on your Mac. No bot, no account, no cloud. Local transcription, speaker separation, plain files.
Murmur
Fast, private, on-device dictation for Windows, Linux, and macOS. Hotkey to speak, text appears in any app. Whisper/Parakeet STT, meeting transcription with speaker labels, local…
Trtc AI Build Quickly
Quickly build real-time AI voice conversation apps with TRTC. Supports multi-agent selection, LLM integration, and TTS/STT services.
fasuizu-br/brainiall-mcp-server
speech with multiple voices.
Elevenlabs CLI
Community-built CLI for the ElevenLabs AI audio platform with TTS, STT, voice tools, and MCP server mode.
eviscerations/whisper-windows-mcp
native local audio and video transcription using whisper.cpp with Vulkan GPU acceleration. No cloud APIs, no Python. Batch processing, multilingual support, model management, and…
mohitbadwal/ringback
hosted pieces (SIP via pjsua2/Linphone + whisper.cpp STT + macOS say TTS). No paid telephony, no extra API key for the conversation.
spokenmd/spoken
Fetch published podcast transcripts as clean Markdown with real speaker names (not "Speaker 1") via the [Spoken](https://spoken.md) API. Search episodes, get transcripts, check cr…
ankurmans/pepys-mcp
mcp`. 99+ languages.
HAL9000
The world's first all-seeing, all-hearing, (almost) all-doing AI agent.
Vzt Flow
Local, private, on-device voice dictation. Hold a key, talk, and the transcript lands at your cursor. Free, offline, and signed + notarized by Apple, so it just opens. Parakeet TD…
Diariz
Self-hosted, multi-user transcription platform: record or upload audio. Speaker-labeled, timestamped transcripts, Recognize speakers across recordings, Summarize, extract action i…
Vidscribe
🎬 MCP Server + Agent Skill + CLI — Transcribe any video URL to text. Plug into Claude Desktop / Cursor / Windsurf / Codex. Supports Bilibili, YouTube, TikTok, 1000+ sites × 5 ASR…
Voxnote
Windows desktop app for cloud audio transcription and speaker diarization (AssemblyAI / Deepgram / Gladia / Speechmatics) with KZ+RU+EN code-switching, LLM task extraction to Line…
Appoiint
Agent communication platform CLI. Slack for Agents. Meetings too. 36 MCP tools.
AbhiMeet
Free open-source meeting recorder with AI transcription & reporting. Fireflies.ai alternative. Records audio + screen, transcribes with Whisper AI in 90+ languages, generates meet…
Feedbacks
Point-and-talk feedback capture for AI analysis. Share your screen, click on things, say what you think.
Whisper Telegram MCP
Two-way voice for Claude via Telegram — Whisper transcription + Kokoro/OpenAI TTS as an MCP server
Alephra
AI medical assistant that analyzes reports, tracks vitals/labs, manages prescriptions, and provides health insights. Features voice interaction in 10+ languages, cloud sync, and a…
Oruk MCP
Hosted MCP server for the oruk Speech API: transcription + speech emotion/tone analysis for coding agents. No local install.
Speech To Text
🎙️ MCP Speech-to-Text Server with Enhanced Cantonese Support | Offline Vosk + Online Google Cloud | Auto-detection for zh-HK | n8n workflows | Hong Kong optimized 🇭🇰
Hlid
A mobile Windows command center for Claude, Codex, OpenCode, and other ACP agents working across your Obsidian vault and projects, with persistent chats, visible tool use, approva…
Ari VoiceCommand
Open-source Windows AI voice assistant and autonomous desktop agent built with Python/PySide6. Supports wake words, speech-to-text, text-to-speech, local LLMs with Ollama, MCP too…
Class Notes MCP
"Modular Python system for recording, transcribing, and generating class notes."
Qirrel
Fast, deterministic NLP entity extraction and transcript cleaning pipeline with LLM adapters and MCP server support for AI Agents.
Cosurg
One field: the clinician says what they are looking at, and the app works out what they need - a led assessment, a sourced answer or a treatment lookup, each traced to a named cli…
Kensho
Kensho — independent third-party profile of a public API surface, by API Evangelist. Kensho Technologies is the AI innovation hub of S&P Global, building machine learning and AI s…
Douyin Transcript MCP
Local-first, read-only Douyin speech transcription MCP using Qwen3-ASR and OpenAI Secure MCP Tunnel; no VPS required.
Observer Skill
Study a hard video with your coding agent: one Node service transcribes it, serves the player page, and exposes MCP tools so the agent answers at your exact pause point and render…
Voxai MCP
Companion MCP server for VoxAI — gives your AI ears (live meeting transcripts) and a voice (speech on your Mac). Runs locally.
Claude Voice Interaction
Local voice interface for Claude Code — TTS + STT on Apple Silicon