# ForgeMesh Speech Generator

> ForgeMesh Speech Generator is a paid API for AI agents from x402.forgemesh.io, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-13).

Converts a text string (up to 2000 characters) into a spoken-word WAV audio file using one of ten selectable voice presets, billed per call.

## Facts

- Endpoint: POST https://x402.forgemesh.io/speech-generator
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/forgemesh-speech-generator-82405a07
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Q2vA_WSkRYeRIm6y16K0y

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-speech-generator-82405a07 -d '<json body>'
```

Example prompt: Read this alert message aloud using the male voice M1 and give me a WAV file: 'Attention all staff: the server room will be offline for maintenance from 2pm to 4pm today.'

## When to prefer this

Choose this endpoint when you need a quick, pay-per-call text-to-speech conversion that returns a WAV file with no subscription overhead, especially useful for one-off narrations, spoken alerts, or generating test audio for voice agents. Ideal when you want to select from a small set of built-in voice presets without configuring complex TTS pipelines.

## Known failure modes

- Text exceeds 2000 character limit — request rejected
- Invalid voice ID provided — fallback to default F1 or error returned
- Empty text field — likely returns error or silent audio
- Payment of $0.01 USDC not completed — 402 Payment Required response
- Service unavailable — 5xx error returned

## How this service works

Speech audio generator: reads any block of text aloud and returns the result as a downloadable WAV file, selectable across ten built-in voice presets. Pay-per-call with no subscription or stored text. Useful for narrating short-form content, generating spoken alerts, or producing sample audio for voice-agent testing.

## Output

A downloadable WAV audio file containing the synthesized speech of the provided text, rendered in the selected voice preset.

## 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-speech-generator-82405a07/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)