What it does
The Text to Speech API is an MCP server with one tool, media_text_to_speech, which converts text into speech audio using the Google TTS engine and returns base64-encoded MP3 audio in JSON. Each request accepts up to 200 characters and an optional language code (default en), covering 20+ languages according to the publisher's documentation.
It suits generating audio narration, building voice assistants, creating audio versions of articles, accessibility features and language learning apps. For language detection, text translation or OCR from images, the documentation points to other tools.
Each call is paid individually through x402 in USDC on Base L2, with no API key or signup. Any x402-aware client, such as @x402/fetch, x402-agent-tools or ATXP, handles the payment cycle. The listed price is $0.012 per call, and payment is processed by Coinbase CDP with PayAI as fallback. The resource is part of the klymax402 marketplace of 100 x402 micropayment APIs that share one wallet. It is released under the MIT license.
Limitations and requirements
Requires an x402-aware client and a wallet holding USDC on Base L2 to pay for each call. Text is limited to 200 characters per request. Each call carries a listed price of $0.012.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
Text to Speech API
Convert text to MP3 speech audio in 50+ languages. x402 micropayment.
v1.1.0As shown on registry.modelcontextprotocol.io when we last read it