# ForgeMesh Text-to-Speech (Long-Form)

> ForgeMesh Text-to-Speech (Long-Form) is a paid API for AI agents from tts.forgemesh.io, paid per call via x402, $0.003/call, status unknown (last checked 2026-09-14).

Converts up to 2000 characters of text into spoken audio (WAV/FLAC/OGG) across 31 languages using a selection of male and female voices, paid per-call via x402 micropayments with no API key required.

## Facts

- Endpoint: POST https://tts.forgemesh.io/v1/audio/speech-long
- Price: $0.003/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/forgemesh-text-to-speech-long-form-48b0db5c
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_RmccUYKNJFCvUXzX1cT8t

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-long-form-48b0db5c -d '<json body>'
```

Example prompt: Read this script aloud using a female voice (F2) and give me a WAV file: 'Welcome to ForgeMesh. Your AI-powered audio experience starts here. This message is available in 31 languages.'

## When to prefer this

Choose this endpoint when you need OpenAI-compatible TTS without managing API keys, want to pay per call via x402 USDC micropayments, need multilingual support across 31 languages, or want a choice of 10 distinct voices (5 male, 5 female). It is especially well-suited for agents that already handle x402 payment flows and need audio generation as a drop-in capability without account provisioning.

## Known failure modes

- Payment failure: x402 micropayment not processed or insufficient USDC balance — request rejected before synthesis
- Input too long: text exceeds 2000 characters — validation error returned
- Invalid voice ID: value outside M1-M5/F1-F5 enum — bad request error
- Unsupported format: response_format not in wav/flac/ogg — ignored or error
- Service unavailability: ForgeMesh Voice backend timeout or downtime — 5xx error

## How this service works

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

## Output

Returns an audio file (WAV by default, or FLAC/OGG if specified) containing the synthesized speech for the provided text, using the selected voice. The response is an OpenAI-compatible inline audio payload with the appropriate content-type header (audio/wav, audio/flac, or audio/ogg).

## 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-long-form-48b0db5c/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)