# ForgeMesh Text-to-Speech & Voice Generation

> ForgeMesh Text-to-Speech & Voice Generation is a paid API for AI agents from tts.forgemesh.io, paid per call via x402, $0.001/call, status unknown (last checked 2026-09-15).

Converts text to spoken audio (WAV/FLAC/OGG) in 31 languages using 10 distinct voices, paid per-call via x402 micropayment with no API key required.

## Facts

- Endpoint: POST https://tts.forgemesh.io/v1/audio/speech
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/forgemesh-text-to-speech-voice-generation-4f74cff2
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_0jll0ZdHRoiqnCXll_dG9

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-voice-generation-4f74cff2 -d '<json body>'
```

Example prompt: Can you turn this text into spoken audio using a female voice (F2) in WAV format: 'Welcome to our platform. We're glad you're here.'

## When to prefer this

Choose ForgeMesh TTS when you need pay-per-call speech synthesis with no API key registration, no subscription, and no monthly commitment — ideal for agents that call TTS infrequently or need to spin up quickly. It is OpenAI-compatible, so switching cost is low. Prefer this over OpenAI TTS or ElevenLabs when you want x402 micropayment billing and broad language coverage (31 languages) with a simple 10-voice palette.

## Known failure modes

- Text input exceeds 2000 characters — request rejected with error
- Invalid voice identifier (not in M1-M5 or F1-F5) — bad request error
- Payment via x402 fails or insufficient USDC balance — 402 Payment Required response
- Unsupported language or character set in input — may produce degraded or silent output
- Invalid response_format value — falls back to WAV or returns error

## How this service works

Paid text-to-speech via x402. WAV audio in 31 languages, OpenAI-compatible, no API keys.

## Output

Returns a binary audio file (WAV, FLAC, or OGG) containing the synthesized speech rendered by ForgeMesh Voice. The response content type is audio/wav (or the requested format), and the audio can be played back directly or saved to disk. No JSON wrapper — it is a raw audio stream.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "input": {
   "type": "string",
   "maxLength": 2000,
   "minLength": 1,
   "description": "OpenAI-compatible text input to synthesize, max 2000 characters"
  },
  "model": {
   "type": "string",
   "description": "Ignored — always uses ForgeMesh Voice"
  },
  "voice": {
   "enum": [
    "M1",
    "M2",
    "M3",
    "M4",
    "M5",
    "F1",
    "F2",
    "F3",
    "F4",
    "F5"
   ],
   "type": "string",
   "description": "Standard voice: M1-M5 or F1-F5"
  },
  "response_format": {
   "enum": [
    "wav",
    "flac",
    "ogg"
   ],
   "type": "string",
   "description": "Requested audio format"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "description": "OpenAI-compatible inline speech audio response",
  "content_type": "audio/wav"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/forgemesh-text-to-speech-voice-generation-4f74cff2/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from tts.forgemesh.io](https://www.zero.xyz/host/tts.forgemesh.io/llms.txt)