Text to speech API: turn text into an audio file (MeloTTS)
Turn up to 1,000 characters of text into natural speech as an audio file (base64, with its content type), in English, Spanish, French, Chinese, Japanese or Korean, with MeloTTS. Use for voice replies, audio notes, accessibility and phone or chat bots.
When to use it
- Voice replies, audio notes, accessibility and phone or chat bots
- Speak up to 1,000 characters in English, Spanish, French, Chinese, Japanese or Korean
Inputs
| Name | Type | Description |
|---|---|---|
text (required) | string | Text to speak, up to 1,000 characters |
lang | string | Language: en, es, fr, zh, ja or ko (default en). One of: en, es, fr, zh, ja, ko. |
Request
Over HTTP, with a card key from /credits:
curl -H "Authorization: Bearer adt_…" "https://tools.funwords.eu/ai/speech?text=Your%20payment%20was%20received.%20Thank%20you!"Or one of your 25 free calls, no key:
curl "https://tools.funwords.eu/ai/speech?text=Your%20payment%20was%20received.%20Thank%20you!&trial=1"Without a key, the same URL answers 402 Payment Required with x402 and MPP terms, so an agent with a wallet pays per call in USDC (Base, Polygon, Arbitrum or Solana over x402; Base or Tempo over MPP) and retries.
Example result
{
"contentType": "audio/wav",
"audioBase64": "UklGRiTJAgBXQVZFZm10IBAAAAABAAEAgLsAAAB3AQACABAAZGF0YQ…",
"bytes": 182630,
"lang": "en",
"characters": 37,
"model": "@cf/myshell-ai/melotts"
}From an AI agent (MCP)
Add the MCP server to Claude, Cursor or any MCP client. This tool is ai_speech, and the first 25 successful calls are free:
https://tools.funwords.eu/mcpQuestions
What do I get back?
The audio as base64 with its content type and size in bytes.
How do I pay?
Each successful call costs $0.01; failed calls are not charged. The first 25 calls are free. Then pay with card credits (from $1; the key goes in an Authorization header or, for clients that can only fetch a URL, as api_key= in the URL) or per call in USDC over x402 or MPP. No account is needed.