# ForgeMesh Text-to-Speech API

> ForgeMesh Text-to-Speech API is a paid API for AI agents from x402.forgemesh.io, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-16).

Converts up to 2000 characters of text into natural-sounding speech audio (WAV, base64-encoded) using a locally-hosted neural speech engine, with 10 selectable voices and no API key required.

## Facts

- Endpoint: POST https://x402.forgemesh.io/text-to-speech
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-16
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/forgemesh-text-to-speech-api-d3ed7c03
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_cPoKPdTlcH2GZ7iCuP_22

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 forgemesh-text-to-speech-api-d3ed7c03 -d '<json body>'
```

Example prompt: Read this message aloud using a female voice (F2): 'Your appointment is confirmed for Thursday at 3pm. Please arrive 10 minutes early and bring your ID.' Give me back the audio as a WAV file.

## When to prefer this

Choose this endpoint when you need quick, pay-per-call text-to-speech synthesis without committing to an API key or subscription. Ideal for voice agents, IVR systems, audio notifications, and short-form audio content where text is under 2000 characters. Prefer it over voice.forgemesh.io's full product when you only need 1 of 10 basic voices and don't require the full 20-voice/31-language tier.

## Known failure modes

- Text exceeds 2000 character limit — request rejected
- Invalid voice ID provided (not in F1-F5 or M1-M5 range) — defaults to F1 or returns error
- Payment not included or insufficient USDC — 402 Payment Required response
- Empty text input — may return error or silent audio
- Unsupported language/character set — may produce degraded or incorrect audio

## How this service works

Text-to-speech API: convert up to 2000 characters into natural speech (WAV, base64) using our locally-hosted neural speech engine — no API keys, pay per call with USDC. Choose voices F1-F5/M1-M5. Use for voice agents, notifications, audio content, and IVR. Text never stored. Full 20-voice / 31-language tiered product at voice.forgemesh.io.

## Output

Returns synthesized speech as a WAV audio file encoded in base64, produced by a locally-hosted neural speech engine. The audio represents the input text spoken in the selected voice. Text is not stored after processing.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "description": "Text to speak, max 2000 chars"
  },
  "voice": {
   "type": "string",
   "description": "Voice id, e.g. F1, M1 (default F1)"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "voice": "F1",
  "characters": 38,
  "audio_base64": "UklGRiQAAABXQVZF...",
  "content_type": "audio/wav"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/forgemesh-text-to-speech-api-d3ed7c03/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from x402.forgemesh.io](https://www.zero.xyz/host/x402.forgemesh.io/llms.txt)