# Arch Tools Text-to-Speech

> Arch Tools Text-to-Speech is a paid API for AI agents from archtools.dev, paid per call via x402, $0.1/call, status unknown (last checked 2026-09-13, last successful call 2026-08-05).

Converts text (up to 5,000 characters) into spoken audio using ElevenLabs voices, paid per-call in USDC on Base

## Facts

- Endpoint: POST https://archtools.dev/v1/tools/text-to-speech
- Price: $0.1/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-13
- Last successful call: 2026-08-05
- Activations on Zero: 3
- Tags: x402
- Canonical page: https://www.zero.xyz/c/arch-tools-text-to-speech-d61c0c7b
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_tYhAEEGcT3VB3wjP6cIrd

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 arch-tools-text-to-speech-d61c0c7b -d '<json body>'
```

Example prompt: Can you read this product description aloud using the ElevenLabs turbo model — here's the text: 'Welcome to our store. We offer handcrafted goods made with care and delivered to your door.' Keep the voice stability at 0.5 and similarity boost at 0.8.

## When to prefer this

Choose this endpoint when you need pay-per-call text-to-speech with no subscription required, settled in USDC on Base via x402. It is particularly useful for agents that need on-demand voice synthesis with fine-grained ElevenLabs voice tuning (model selection, voice ID, stability, similarity boost) without managing API keys for ElevenLabs directly. Prefer it over direct ElevenLabs integration when you want crypto-native micropayment billing or when operating within the Arch Tools ecosystem alongside sibling tools.

## Known failure modes

- Text exceeds 5,000 character limit — request rejected
- Invalid ElevenLabs model_id or voice_id — synthesis fails
- Stability or similarity_boost values outside 0-1 range — validation error
- Payment not fulfilled in USDC on Base — 402 response returned
- Empty or missing 'text' field — required field error

## How this service works

Convert text to natural-sounding audio via ElevenLabs (returns base64 MP3). Pay per call with USDC (x402) or credits - archtools.dev

## Output

A JSON response containing the synthesized audio output generated from the provided text, using the specified ElevenLabs model and voice configuration with the requested stability and similarity boost parameters.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "description": "Text to convert (max 5,000 chars)"
  },
  "model_id": {
   "type": "string",
   "description": "ElevenLabs model ID (default: eleven_turbo_v2_5)"
  },
  "voice_id": {
   "type": "string",
   "default": "EXAVITQu4vr4xnSDxMaL",
   "description": "ElevenLabs voice ID"
  },
  "stability": {
   "type": "number",
   "description": "Voice stability 0-1 (default: 0.42)"
  },
  "similarity_boost": {
   "type": "number",
   "description": "Voice similarity boost 0-1 (default: 0.82)"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/arch-tools-text-to-speech-d61c0c7b/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from archtools.dev](https://www.zero.xyz/host/archtools.dev/llms.txt)