# MapleAI Text-to-Speech API (x402 Pay-Per-Request)

> MapleAI Text-to-Speech API (x402 Pay-Per-Request) is a paid API for AI agents from base.mapleai.shop, paid per call via x402, $0.016/call, status unknown (last checked 2026-10-11).

Synthesizes spoken audio from text using multiple TTS models including Gemini Flash and Groq Orpheus, returning a WAV audio stream, paid per request in USDC via x402.

## Facts

- Endpoint: POST https://base.mapleai.shop/v1/audio/speech?utm_source=zero.xyz
- Price: $0.016/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-11
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/mapleai-text-to-speech-api-x402-pay-per-request-ceba764f
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_QmN0ZThdJ5MUyg6zd3yIc

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability mapleai-text-to-speech-api-x402-pay-per-request-ceba764f -d '<json body>'
```

Example prompt: Can you read this out loud using the Orpheus English model with the 'autumn' voice — here's the text: 'Welcome to our quarterly review. Things are going really well this year [laughs].'

## When to prefer this

Choose this endpoint when you need pay-per-use TTS without a subscription, especially when you want emotive speech with emotion tags (e.g. [laughs]) via Groq Orpheus, or Arabic-language voice synthesis. Ideal for agents that generate audio on demand and pay per call in USDC on Base. Prefer over OpenAI TTS directly if you want crypto-native billing or access to Orpheus voices not available on OpenAI.

## Known failure modes

- Input text exceeds 5000 characters — request rejected
- Invalid model name supplied — enum validation error
- Invalid voice name for selected model — may fall back to default or error
- Payment not settled via x402 — 402 Payment Required response
- Speed value outside 0.25–4.0 range — validation error
- Groq Orpheus model unavailable — upstream service error

## How this service works

14 chat models (GPT + Claude), 7 image models, and Jev structured decisions. Pay per request in USDC on Base with x402.

## Output

A binary WAV audio stream in RIFF/WAVE format at 24 kHz mono, returned as audio/wav content. The audio contains the synthesized speech of the provided input text using the selected model and voice.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "input": {
   "type": "string",
   "description": "Text to synthesize, 1-5000 characters"
  },
  "model": {
   "enum": [
    "tts-1",
    "tts-1-hd",
    "orpheus-english",
    "orpheus-arabic"
   ],
   "type": "string",
   "description": "tts-1 = fast Gemini Flash-Lite, tts-1-hd = fuller Gemini Flash, orpheus-english/orpheus-arabic = emotive Groq Orpheus (en voices autumn/diana/hannah/austin/daniel/troy, ar voices fahad/sultan/noura/lulwa/aisha/abdullah; emotion tags like [laughs] supported)"
  },
  "speed": {
   "type": "number",
   "maximum": 4,
   "minimum": 0.25
  },
  "voice": {
   "type": "string",
   "description": "Voice preset (alloy, echo, fable, onyx, nova, shimmer…) or a Gemini voice name; default alloy"
  },
  "response_format": {
   "enum": [
    "wav"
   ],
   "type": "string",
   "default": "wav"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "audio": "binary WAV stream (audio/wav)",
  "format": "RIFF/WAVE 24 kHz mono"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/mapleai-text-to-speech-api-x402-pay-per-request-ceba764f/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from base.mapleai.shop](https://www.zero.xyz/host/base.mapleai.shop/llms.txt)