MCP CheckMCP servers for text to speech
27 servers from the official MCP Registry that work with text to speech. 17 need no API key and 13 can run hosted. Each row shows the security checks, the secrets asked for and an install command.
text to speech MCP servers 27
Now showing are unlisted. These entries didn't pass our listing filter: no source repo, a very short or duplicated description, or a publisher with 100+ servers. Same automated checks, shown as-is. How we check
| Type | Secrets | Version | Actions | ||||
|---|---|---|---|---|---|---|---|
 ★ 3 io.github.fasuizu-br/speech-ai Pronunciation scoring, speech-to-text, and text-to-speech for language learning | 4/4All passed | 45health of 100 | RemoteHosted | Noneno keys asked | 2.3.0 | ||
 ★ 1 audio.ditto/tts Text-to-speech: browse voices and synthesize natural speech from text with ditto.audio. | 3/3All passed | 49health of 100 | RemoteHosted | Noneno keys asked | 1.2.0 | ||
★ 1 io.github.Engr-FaizanAli/text-to-speech Reads text aloud locally on Windows, macOS, and Linux. No API key, account, or cloud service. | 7/7All passed | 49health of 100 | PyPIRuns locally | Noneno keys asked | 0.4.1 | ||
io.github.runapi-builder/gemini-tts-mcp RunAPI MCP server for Gemini TTS: create tasks, poll status, check pricing. | 7/7All passed | 54health of 100 | npmRuns locally | 1secret asked | 0.2.1 | ||
com.unlimitedtts/tts Quote-first, non-custodial x402 text-to-speech with spend policy, MP3 artifacts, and receipts. | 7/7All passed | 51health of 100 | npmRuns locally | Noneno keys asked | 0.1.0 | ||
io.github.mrfqcentic/mcp-kokoro-tts Local Kokoro-82M TTS MCP server that synthesizes and plays speech on your machine | 7/7All passed | 50health of 100 | PyPIRuns locally | Noneno keys asked | 0.1.4 | ||
★ 1.4k dev.voicemode/voicemode Natural voice conversations for AI assistants - STT/TTS via MCP | 6/71 warning | 82health of 100 | PyPIRuns locally | 1secret asked | 9.0.1 | ||
 ★ 256 io.github.nirholas/audio-mcp Text-to-speech, speech-to-text, audio-to-face lipsync, and motion-capture clips for 3D agents. | 7/7All passed | 76health of 100 | npmRuns locally | 1secret asked | 0.1.3 | ||
★ 219 io.github.RLabs-Inc/gemini-mcp Gemini 3 MCP server with 30+ tools: images, video, research, TTS, code exec & CLI | 6/71 warning | 57health of 100 | npmRuns locally | 1secret asked | 0.7.1 | ||
★ 13 io.github.mindstone/mcp-server-elevenlabs ElevenLabs MCP server: TTS, music, sound effects, voices, and audio transcription | 7/7All passed | 56health of 100 | npmRuns locally | 1secret asked | 0.5.2 | ||
 ★ 10 com.paxalabs/mcp Thai, English, Mandarin speech AI: TTS with playback, transcription, translation, OCR, extraction | 7/7All passed | 57health of 100 | npmRuns locally | 1secret asked | 0.1.0-beta.16 | ||
★ 7 io.github.psyb0t/talkies Self-hosted MCP server for speech: ASR transcription, TTS synthesis, and file staging tools. | 4/4All passed | 57health of 100 | DockerRuns locally | Noneno keys asked | 0.17.0 | ||
★ 4 io.studiomeyer/video Video production: recording, editing, effects, captions, TTS, screenshots. 8 tools. | 7/7All passed | 60health of 100 | npmRuns locally | Noneno keys asked | 1.0.3 | ||
★ 2 io.github.user-github-me/soniccraft Compile timelines of TTS speech, music and SFX into ducked, loudness-mastered audio with subtitles | 4/51 warning | 43health of 100 | DockerRuns locally | 3secrets asked | 0.1.0 | ||
 ★ 2 pro.bananabanana/image-video Images, video & speech: Nano Banana, GPT Image, Veo, Omni, Wan, Grok, Gemini TTS. Crypto or card. | 3/3All passed | 55health of 100 | RemoteHosted | Noneno keys asked | 1.0.13 | ||
★ 1 app.apick/all APICK Korean data, building register, simple-auth lookups, OCR, search, image, video and TTS | 8/8All passed | 56health of 100 | npmLocal or hosted | 1secret asked | 5.0.0 | ||
★ 1 io.github.AceDataCloud/mcp-fish MCP server exposing the AceDataCloud Fish Audio API (text-to-speech with voice conditioning) | 8/8All passed | 61health of 100 | PyPILocal or hosted | 1secret asked | 2026.10.18.5 | ||
★ 1 app.apick/convert File conversion: PDF, DOCX, STT, asynchronous TTS with MP3/ASS downloads, watermarking | 4/4All passed | 45health of 100 | RemoteHosted | Noneno keys asked | 2.0.0 | ||
★ 1 io.github.boska/vox Native macOS MCP server for voice I/O — Swift binary, SFSpeechRecognizer + ElevenLabs TTS. | 4/4All passed | 39health of 100 | MCPBRuns locally | 1secret asked | 1.0.0 | ||
★ 1 io.github.deapi-ai/mcp-server-deapi 35 AI tools for image/video generation, TTS, transcription, OCR & embeddings via deAPI | 3/3All passed | 49health of 100 | RemoteHosted | Noneno keys asked | 0.3.0 | ||
io.github.AndriyVK/apify-document-tools Documents to Markdown and PDF, OCR, transcription, TTS, screenshots, domain checks, video frames. | 3/3All passed | 49health of 100 | RemoteHosted | Noneno keys asked | 0.3.0 | ||
io.github.ghlee0786/flow-learning-system Build motion-graphics lessons with sentence-synced TTS for any subject: one sentence, one scene. | 5/61 warning | 42health of 100 | MCPBRuns locally | Noneno keys asked | 0.1.0 | ||
io.github.CalmNguyen/ttsforfree Generate AI voices, text-to-speech, subtitles, transcription, and video localization. | 4/4All passed | 43health of 100 | RemoteHosted | Noneno keys asked | 1.0.0 | ||
io.github.GRQDigitalCapital/giggy-mcp Giggy speech tools for AI agents: discover voices and generate text-to-speech. | 3/3All passed | 49health of 100 | RemoteHosted | Noneno keys asked | 1.0.2 | ||
io.github.bilbop1/bilbop-x402 Pay-per-call summarize, Solana data, TTS, and brand feedback via api.bilbop.org. | 4/4All passed | 43health of 100 | RemoteHosted | Noneno keys asked | 1.0.0 | ||
io.github.MintMachineHQ/baron-power-play Pay-per-call AI infra for agents: DeFi market data, LLM inference, STT/TTS. x402 v2, USDC on Base. | 4/4All passed | 44health of 100 | RemoteHosted | Noneno keys asked | 1.0.0 | ||
io.github.pawelmamcarz/przypominamy Polish SMS & voice gateway: send SMS/TTS, contacts, blacklist, tracked links, replies, reports. | 4/4All passed | 46health of 100 | RemoteHosted | Noneno keys asked | 1.3.0 |
Showing 1 to 27 of 27. These are the most recently updated; search or pick a category for the rest.
text to speech MCP servers: what to know before you pick one
What is the best MCP server for text to speech?
Among community builds, the most-starred on GitHub are Speech AI - Pronunciation, STT & TTS (★ 3), ditto.audio (★ 1) and Text to Speech (★ 1). If you want one that passed every check, Speech AI - Pronunciation, STT & TTS did.
Is it safe to give an AI a text to speech MCP server?
On registry checks, 23 of 27 come out clean. We also read the code or live tool list of 19 of them without running anything, and 2 raised a warning worth reading, such as an install script or text aimed at the AI. Treat a pass as "nothing found", and give any server the least access that works.
Which text to speech MCP servers need no API key?
17 of the 27 list no secrets, including Speech AI - Pronunciation, STT & TTS, ditto.audio and Text to Speech. Some still ask you to sign in once they run.
Who makes these text to speech MCP servers?
No company-verified one yet (checked 31 Oct 2026). All 27 text to speech servers are community builds from 26 different publishers, so check who is behind one before you hand it a text to speech key.
How do I add a text to speech MCP server to Claude?
To connect text to speech through Speech AI - Pronunciation, STT & TTS, run this in a terminal: claude mcp add --transport http speech-ai https://apim-ai-apis.azure-api.net/mcp/pronunciation/mcp. Pin the version shown before you rely on it.
Do I have to install a text to speech MCP server?
13 can run hosted, so you only paste a URL into Claude, Cursor or VS Code. The 16 that run locally ship as 8 npm, 4 PyPI, 2 Docker and 2 MCPB bundle packages.
More topics: every “MCP server for…” page. Prefer a skill? Claude skills for this (78).