# Automaton Media Text-to-Speech API

> Automaton Media Text-to-Speech API is a paid API for AI agents from api.language123.net, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-11).

Converts text to natural English speech audio (MP3 or WAV) with selectable voice and speed, billed per 1,000 characters via USDC on Base

## Facts

- Endpoint: POST https://api.language123.net/v1/tts?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-11
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/automaton-media-text-to-speech-api-f0fcf3f6
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_4ehuT-6xZJvktBHmLS7Rg

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 automaton-media-text-to-speech-api-f0fcf3f6 -d '<json body>'
```

Example prompt: Read the following blog intro aloud in the af_heart voice at normal speed and give me the result as an MP3: 'Welcome to our weekly roundup of the latest in AI research and development.'

## When to prefer this

Choose this endpoint when you need quick, pay-per-use text-to-speech synthesis with no account setup, especially for AI agent workflows where dynamic narration is needed on demand. It is ideal for low-volume or sporadic TTS needs billed in micropayments via crypto (USDC on Base), eliminating subscription friction. Prefer it over subscription TTS APIs when the agent needs to generate audio without pre-registered credentials.

## Known failure modes

- Text too long — no explicit max length documented but very large inputs may time out or incur higher cost
- Invalid voice_id — returns error if the specified voice is not found in GET /v1/voices
- Invalid speed value — must be between 0.5 and 2.0, values outside range are rejected
- Invalid format enum — only 'mp3' and 'wav' are accepted
- Payment failure — if USDC balance is insufficient or x402 payment header is malformed, request is rejected with 402
- Empty text field — submitting blank or missing text returns a validation error

## How this service works

Pay-per-use APIs for AI agents: YouTube and audio transcription (speech-to-text); Text-to-speech: natural English voices (MP3/WAV); Text-to-image generation; Web scraper: any URL to clean Markdown; YouTube transcript (captions, instant). Pay each request with USDC via x402 on Base - no signup, no API key.

## Output

A binary audio file (MP3 or WAV) containing the synthesized speech of the submitted text, ready for playback or storage. The audio quality reflects a natural English voice at the chosen speed.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "description": "Text to speak (price is per 1,000 characters)"
  },
  "speed": {
   "type": "number",
   "maximum": 2,
   "minimum": 0.5
  },
  "format": {
   "enum": [
    "mp3",
    "wav"
   ],
   "type": "string"
  },
  "voice_id": {
   "type": "string",
   "description": "Voice from GET /v1/voices (default af_heart when available)"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": "<binary audio: MP3 (audio/mpeg) or WAV (audio/wav), 24 kHz mono>"
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/automaton-media-text-to-speech-api-f0fcf3f6/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.language123.net](https://www.zero.xyz/host/api.language123.net/llms.txt)