# Nova TTS — Text-to-Speech API

> Nova TTS — Text-to-Speech API is a paid API for AI agents from noa.orbonomy.xyz, paid per call via x402, $0.1/call, status unknown (last checked 2026-09-13).

Converts input text to synthesized speech audio, returning binary audio data, paid per call in USDC on Base.

## Facts

- Endpoint: POST https://noa.orbonomy.xyz/api/tts
- Price: $0.1/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/nova-tts-text-to-speech-api-147eb994
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_FrRurU_5WqGm9x2DR1y4z

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 nova-tts-text-to-speech-api-147eb994 -d '<json body>'
```

Example prompt: Read this paragraph aloud for me using Nova TTS and give me the audio file: 'Welcome to our platform. We are thrilled to have you here.' Use the default voice.

## When to prefer this

Choose this endpoint when you need pay-per-call text-to-speech synthesis without a subscription, billed in USDC on Base via x402. Useful for agents that infrequently need audio generation and prefer crypto micropayments over monthly API key plans. Best when the caller can handle binary audio response data directly.

## Known failure modes

- Missing required 'text' field returns a 400 or validation error
- Empty text string may result in empty or invalid audio output
- Invalid or unsupported voice name may fall back to default or return an error
- Payment failure (insufficient USDC balance or x402 rejection) returns a 402 status
- Server-side TTS model unavailability returns a 500 error
- Very long text inputs may be truncated or rejected depending on limits

## How this service works

Pay-per-call AI inference. Chat, reason, translate, analyze, generate. USDC on Base.

## Output

A binary audio file containing the synthesized speech corresponding to the provided text input. The agent receives raw audio data that can be saved, streamed, or played back.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "text"
 ],
 "properties": {
  "text": {
   "type": "string",
   "description": "Text to convert to speech"
  },
  "voice": {
   "type": "string",
   "description": "Voice name (optional)"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "string",
 "format": "binary"
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/nova-tts-text-to-speech-api-147eb994/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from noa.orbonomy.xyz](https://www.zero.xyz/host/noa.orbonomy.xyz/llms.txt)