# DexL Agents Text-to-Speech

> DexL Agents Text-to-Speech is a paid API for AI agents from agents.dexl.io, paid per call via x402, $0.001/call, status unknown (last checked 2026-09-14).

Converts text (up to 5000 characters) into a WAV audio file using a selectable AI voice, billed per call via x402 with no API key required.

## Facts

- Endpoint: POST https://agents.dexl.io/v1/audio/speech
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/dexl-agents-text-to-speech-1408d012
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_5y8SFdZXlzRp3txJYd4aJ

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 dexl-agents-text-to-speech-1408d012 -d '<json body>'
```

Example prompt: Read this out loud in the Aoede voice: 'Welcome to our weekly briefing. Here are the top three stories you need to know about today.' — give me back a WAV file.

## When to prefer this

Choose this endpoint when you need programmatic text-to-speech with no account registration or API key setup, and you want pay-per-call billing via x402 crypto micropayments. It is ideal for AI agents that need to generate audio on demand without managing subscription credentials, and when a choice of named AI voices and WAV output format is sufficient.

## Known failure modes

- Text exceeds 5000 character limit — request rejected or truncated
- Invalid voice name not in the allowed enum (Kore, Puck, Charon, Fenrir, Aoede, Leda, Orus, Zephyr) — error response
- x402 payment failure or insufficient USDC balance — 402 Payment Required response
- Empty or missing input text field — malformed request error
- Upstream TTS model unavailability — 503 or gateway error

## How this service works

Turn text into speech and get a WAV back: eight voices, 24 kHz mono, up to 5000 characters per call. Priced per call with x402, and the quote is a ceiling - pay with the upto scheme and only the audio you actually generated settles.

## Output

Returns a binary WAV audio file in a RIFF/WAVE container, encoded as 24 kHz mono PCM, containing the synthesized speech of the provided text in the selected voice.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "input": {
   "type": "string",
   "description": "Text to speak, up to 5000 characters."
  },
  "voice": {
   "type": "string",
   "description": "One of: Kore, Puck, Charon, Fenrir, Aoede, Leda, Orus, Zephyr."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/dexl-agents-text-to-speech-1408d012/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agents.dexl.io](https://www.zero.xyz/host/agents.dexl.io/llms.txt)