Português
Deutsch
Français
Español
العربية
Italiano
Nederlands
日本語
Русский
Türkçe
Hrvatski
Svenska
Čeština
한국어
Ελληνικά
Polski
ไทย
עברית
Dansk
Suomi
Norsk
Română
Українська
Bahasa Indonesia
中文
Tiếng ViệtWhat is AnyToSpeech MCP?
It's a Model Context Protocol server that lets AI assistants (Cursor, Claude, ChatGPT, VS Code, etc.) call AnyToSpeech on your behalf — text-to-speech, transcription, translation, voice cloning, podcasts, and more.
Connect Cursor, Claude, VS Code, or ChatGPT to your AnyToSpeech account. Convert text, transcribe meetings, clone voices, and generate podcasts — without copy-pasting or a separate API bill.
Uses your existing plan, credits & transcription minutes · Revocable keys · One-click Cursor install
Not a stripped-down API. The same production features your account already has, exposed as tools your assistant can call.
Generate audio from plain text, PDFs, DOCX, images with text, SRT subtitles, or multi-speaker scripts. Perfect for narration, accessibility, and content repurposing.
Submit audio or video for transcription, summarize recordings, translate text, audio, images, or media URLs — all metered against your transcription minutes.
Create custom voices from samples, design new voices with AI, run speech-to-speech conversion, and manage your voice library — all from a chat prompt.
Generate full podcast episodes from a topic, upload a file, or plan a series. Your assistant handles scripting and audio — you keep publishing.
Grant only the permissions each assistant needs. Create separate keys for work vs personal apps.
Text, documents, images, SRT, and multi-speaker dialogue → downloadable audio.
Upload or link media, poll job status, get transcripts and AI summaries.
Translate text, audio, images, and transcripts across languages.
Clone, design, test, convert, and delete custom voices you own.
Single episodes, file uploads, and multi-episode series planning.
Check credits and minutes, list voices, track async jobs, cancel runs.
No developer portal. No separate API subscription. Just your AnyToSpeech account.
Sign up for AnyToSpeech if you haven't already. Free tier included — upgrade anytime for more credits and minutes.
Open AI integrations, pick permissions, and get a one-time key. One-click install for Cursor; copy-paste for Claude and others.
“Transcribe this file.” “Read this PDF aloud.” “Make a podcast about…” Usage bills to your plan automatically.
Unlike generic API keys, MCP connects to your subscription — with controls you can revoke anytime.
It's a Model Context Protocol server that lets AI assistants (Cursor, Claude, ChatGPT, VS Code, etc.) call AnyToSpeech on your behalf — text-to-speech, transcription, translation, voice cloning, podcasts, and more.
No. MCP usage draws from your existing AnyToSpeech account — the same credits, transcription minutes, and plan limits you use on the website.
After creating an integration key, click Add to Cursor on the integrations page. Cursor opens and registers the server automatically with your key.
Yes. Add a custom MCP connector in Claude (Settings → Connectors) or ChatGPT (paid plans with connector support). Paste the server URL and your integration key.
Keys are revocable and scoped. You choose permissions per key. Disconnect anytime from the integrations page — active sessions lose access immediately.
https://anytospeech.com/api/mcp — shown on your integrations page after you sign in, with your personal key.
Connect AnyToSpeech once. Your assistant handles speech, transcription, and podcasts from chat.
Get started — it's free