How do I connect a Speech-to-Text MCP server to Claude Desktop or Cursor?

To install a Speech-to-Text MCP server, select your desired server from the directory, copy the JSON configuration snippet, and add it to your client config file (such as claude_desktop_config.json or .cursor/mcp.json).

Are Speech-to-Text MCP servers free to use?

Yes, all Speech-to-Text MCP servers listed in this directory are open-source and free to integrate into compatible Model Context Protocol clients.

63 Speech-to-Text MCP Servers

Q: What are Speech-to-Text Model Context Protocol (MCP) servers?

Model Context Protocol (MCP) servers in the Speech-to-Text category allow AI assistants (such as Claude Desktop, Cursor, Windsurf, and Cline) to connect directly to speech-to-text tools, APIs, and databases without manual copy-pasting.

Discover 63 Speech-to-Text MCP servers for AI agents. Browse, compare, and install Model Context Protocol tools that connect Claude, Cursor, and other clients to speech-to-text capabilities. Popular picks include FunASR, Whisper Windows MCP, Transcription.

Open in interactive directory

FunASR

Transcribe local audio with FunASR and SenseVoice using private, on-device inference.

0 0 0

Whisper Windows MCP

eviscerations

Windows-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 background job handling built in.

23 3 1

Transcription

AI transcription from URLs. 99% accuracy, speaker diarization, 98+ languages.

0 0 0

Spoken

spokenmd

Fetch published podcast transcripts as clean Markdown with real speaker names (not "Speaker 1") via the Spoken API. Search episodes, get transcripts, check credit balance.

3 0 0

Whisper MCP

Local audio transcription using whisper.cpp. Transcribe with OpenAI Whisper models.

1 0 0

MCP Listen

Give your AI agents the ability to listen. Microphone capture and speech-to-text.

0 0 0

Equalang MCP

Translate documents, subtitles, pictures, audio and video with layout kept; transcribe recordings.

0 0 0

Whisper

Verify Whisper agent identities and look up RDAP for a routable /128 — keyless.

0 0 0

SpeechWeave

Transcribe local files and URLs with SpeechWeave's OpenAI-compatible API.

1 0 0

Windy Word

Control Windy Word voice-to-text from any MCP agent — paste, hotkeys, models, config.

1 0 0

Whisper Graph

Query WhisperGraph: the internet's infrastructure & threat-intel graph (DNS, BGP, GeoIP, WHOIS).

1 0 0

Frenchie

OCR, transcription, and image generation for AI agents via MCP.

0 0 0

Youtube MCP

format37

MCP server that transcribes YouTube videos to text. Uses yt-dlp to download audio and OpenAI's Whisper-1 for more precise transcription than youtube captions. Provide a YouTube URL and get back the full transcript splitted by chunks for long videos.

1 0 0

Transcribe MCP

Transcribe audio/video and find dead air. Pay-per-call in USDC over x402 — no account, no key.

1 0 0

Justtranscribe MCP

Transcribe public videos & audio (YouTube, TikTok, IG) into accurate, timestamped text via API.

1 0 0

Vocce transcribe

Transcribe audio/video to text + SRT/VTT via vocce's hosted Whisper. No API key required.

0 0 0

Ollos MCP

Local, offline transcription, speakers, keyframes, on-screen text and review of any audio or video.

0 0 0

Pepys MCP

ankurmans

Pay-once transcription for audio, video, and whole podcast feeds via Pepys. Transcribe a file or a pasted YouTube/podcast link, get speaker diarization, export SRT/VTT, search a transcript, and check credit balance. Hosted connector (OAuth, no API key) or npx pepys-mcp. 99+ languages.

2 0 0

Transcriptor MCP

samson-art

Transcriptor MCP is your choice when you need transcripts and metadata for AI, summarization, or content analysis

2 0 0

Video Transcriber

Transcribe videos from 1000+ platforms or local files offline, and search across every transcript

1 0 0

Voice Audio MCP

Voice Audio MCP server. Tools: text to speech, list voices, transcribe. Built by MEOK AI Labs.

2 0 0

Ffvoice

Offline speech-to-text & speaker diarization MCP server: transcribe audio on-device, no cloud

0 0 0

MCP Server Alice

Secure audio transcription meets AI. Connect Alice recordings to Claude, ChatGPT, Gemini, and more.

0 0 0

Macwhisper MCP Server

MacWhisper transcription for Claude Desktop. Fully local, no cloud, audio stays on your Mac.

0 0 0

CrispASR Agent Transcriber

Transcribe local audio and video with CrispASR and local models only.

1 0 0

OpenTranscribe MCP

Provider-independent speech-to-text with normalized transcripts over MCP.

0 0 0

Live Audio Intelligence

Live webcast transcription + vocal stress analysis (F0 jitter, hesitation) for earnings calls.

0 0 0

Speko

Official Speko MCP server: build, run, and migrate voice agents (STT/TTS/V2V) for coding agents.

1 0 0

Name Whisper — ENS Intelligence Layer

44 MCP tools to search, value, register, trade, and manage ENS names. AI-powered intelligence layer.

0 0 0

Contendeo

Multimodal video analysis MCP — transcription, vision, and OCR for any video URL.

0 0 0

Tiktok Transcript Scraper

AI speech-to-text for public TikTok videos: SRT, VTT, word timings, speaker labels, 90+ languages.

0 0 0

Speech AI Pronunciation, STT & TTS

Pronunciation scoring, speech-to-text, and text-to-speech for AI agents.

0 0 0

AudioPod AI

Audio AI tools: text-to-speech, voice cloning, music generation, stem separation, transcription.

0 0 0

QuillHub

Meeting transcripts for AI agents: search calls, read who said what, transcribe files and links.

0 0 0

Mac Voice MCP

Talk with your AI assistant out loud on a Mac, with on-device speech recognition (whisper.cpp).

0 0 0

Oruk Speech

Hosted speech-to-text + speech emotion/tone analysis for agents. No install; trial keys built in.

1 0 0

TranscriptMax

Transcribe YouTube via Whisper. Summaries, chapters, semantic-search across your corpus.

1 0 0

Kooma — Bambara AI

Bambara AI over MCP: text-to-speech, transcription and translation (Bamanankan + more).

0 0 0

Editclips

Video, audio, and image processing for AI agents: convert, transcribe, upscale - 150+ operations.

0 0 0

Doseedo

Edit DAW sessions; convert Logic/Ableton/FL/PT/REAPER/Cubase/Dorico; stems, transcribe, generate

0 0 0

Voicely

Offline speech-to-text on macOS: transcribe audio/video files, read dictations and calls.

0 0 0

MCP Transcribe

transcribe-app

This service provides fast and reliable transcriptions for audio/video files and voice memos. It allows LLMs to interact with the text content of audio/video file.

2 0 0

Transkriba — Russian audio transcription

Transcribe Russian audio and video with timestamps and optional speaker labels from files or links.

0 0 0

Lexicon

Fixes the names and jargon speech-to-text gets wrong before your agent acts on a dictated prompt.

0 0 0

Doseedo

Generate music, separate stems, transcribe audio to MIDI, build Logic and Ableton sessions

1 0 0

Kurdish Tts Stt

Kurdish (Sorani & Kurmanji) text-to-speech & speech-to-text — 664 AI voices. API key required.

1 0 0

Whisper Transcribe

Transcribe audio locally with faster-whisper or through the OpenAI Whisper API.

1 0 0

RiverScript

MCP server for RiverScript, an AI transcription platform - fetches transcripts shared via a link.

1 0 0

Transcribe

Transcribe audio and video into speaker-labelled transcripts, subtitles, clips, and cited Q&A.

1 0 0

Zernote

User research workspace to transcribe interviews and turn conversations into insights.

0 0 0

FieldTranscript

Verbatim transcription of public video/audio URLs to clean text, SRT, and timestamped records.

0 0 0

Voice Transcriber MCP Server

MCP server for transcribing Google Chat voice messages using Groq Whisper API

0 0 0

Whispernotes

Search, read, and create speech-to-text transcripts on-device with the Whisper Notes Mac app.

0 0 0

EarScribe MCP

EarScribe is a browser-based transcription tool that converts audio to text on-device using OpenAI

0 0 0

Edict

Search your dictation transcripts and transcribe audio or video on-device, with speaker labels.

0 0 0

Shorty

Summarize and transcribe videos, audio, documents and web pages; subtitles; search your library.

0 0 0

Voibe

Transcribe recordings into a speaker-labelled transcript with timestamps and a summary.

0 0 0

Kurdish Tts Stt

Sorani & Kurmanji TTS+STT: Kurdish speech most APIs lack. 885 voices, free tier, no key to browse.

0 0 0

Conversion Tools

Convert files too big or exotic for a sandbox: 140+ formats, batch, OCR, AI extraction, TTS/STT

0 0 0

Wavenote

On-device dictation, audio transcription, and notes management for macOS. Local stdio MCP server to search notes, manage tasks, and transcribe audio with zero external dependencies.dictation, transcription, notes, macos, local-firstProprietaryhttps://wavenote.featurebase.app/https://getwavenote.com/mcppython3mcp/wavenote_mcp.py

4 0 0

Browse all 63 Speech-to-Text servers →

Explore related categories

Frequently Asked Questions about Speech-to-Text MCP Servers

Model Context Protocol (MCP) servers in the Speech-to-Text category allow AI assistants (such as Claude Desktop, Cursor, Windsurf, and Cline) to connect directly to speech-to-text tools, APIs, and databases without manual copy-pasting.