# Treza Labs Text-to-Speech (ElevenLabs)

> Treza Labs Text-to-Speech (ElevenLabs) is a paid API for AI agents from www.trezalabs.com, paid per call via x402, $0.35/call, status healthy (last checked 2026-10-02, last successful call 2026-10-02).

Converts text (up to 3000 characters) into a natural-sounding MP3 voiceover using ElevenLabs Eleven v3 or Multilingual v2, with 13 voice choices, returned in the same response.

## Facts

- Endpoint: POST https://www.trezalabs.com/api/x402/speech?utm_source=zero.xyz
- Price: $0.35/call
- Payment: x402
- Status: healthy
- Last checked: 2026-10-02
- Last successful call: 2026-10-02
- Success rate: 100% of calls made through Zero
- Rating: 4.7 / 5 from 1 review
- Activations on Zero: 3
- Tags: x402
- Canonical page: https://www.zero.xyz/c/treza-labs-text-to-speech-elevenlabs-db39a596
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_dfIczKKRSVG37glmCOvM1

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 treza-labs-text-to-speech-elevenlabs-db39a596 -d '<json body>'
```

Example prompt: Read this out loud in the 'lily' voice using the expressive eleven-v3 model: 'Welcome to our annual summit. We're thrilled to have you here today — let's make this a morning to remember.'

## When to prefer this

Choose this endpoint when you need a high-quality, expressive AI voice narration returned synchronously as an MP3 in a single API call, without managing an ElevenLabs account or API key. It is ideal for agents that need quick one-off voiceovers, multilingual narration across 29 languages, or expressive speech with inline direction cues like [whispers]. Prefer it over raw ElevenLabs integration when you want pay-per-use USDC micropayments with no subscription overhead.

## Known failure modes

- Text exceeds 3000 character limit — request rejected
- Invalid voice or model enum value — validation error
- Payment not included or insufficient USDC — 402 response
- Empty text field — required field validation failure
- Service unavailable from ElevenLabs backend — 5xx error

## How this service works

Text to speech: send text, get a natural voiceover MP3 back in the same response. ElevenLabs Eleven v3 (expressive, takes [whispers]-style directions) or Multilingual v2 (29 languages), a choice of ElevenLabs narrators, up to 3000 characters, $0.42 per 1,000 characters. GET this URL for the voices. No account or API key: the payment is the only credential.

## Output

A binary MP3 audio file returned directly in the HTTP response body, containing the synthesized speech of the provided text in the selected voice and model. The audio is ready to play, save, or pipe into downstream processing immediately.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method",
    "bodyType",
    "body"
   ],
   "properties": {
    "body": {
     "type": "object",
     "required": [
      "text"
     ],
     "properties": {
      "text": {
       "type": "string",
       "maxLength": 3000,
       "description": "What to say."
      },
      "async": {
       "type": "boolean",
       "default": false,
       "description": "true: answer 202 with a statusUrl at once."
      },
      "model": {
       "enum": [
        "eleven-v3",
        "eleven-multilingual-v2"
       ],
       "type": "string",
       "default": "eleven-v3"
      },
      "voice": {
       "enum": [
        "george",
        "daniel",
        "callum",
        "alice",
        "lily",
        "brian",
        "adam",
        "asher",
        "archie",
        "mark",
        "piper",
        "rachel",
        "charlie"
       ],
       "type": "string",
       "default": "george"
      }
     },
     "additionalProperties": false
    },
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "POST"
     ],
     "type": "string"
    },
    "bodyType": {
     "enum": [
      "json",
      "form-data",
      "text"
     ],
     "type": "string"
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "audio": "https://www.trezalabs.com/api/media/generated/x402_speech/1a2b3c4d.mp3?s=...&c=...",
  "model": "eleven-v3",
  "runId": "2026-09-23T18:04:11.000Z#1a2b3c4d",
  "voice": "george",
  "status": "success",
  "paidUsd": 0.04,
  "statusUrl": "https://www.trezalabs.com/api/x402/speech?runId=...&token=...",
  "characters": 84,
  "transaction": "0x..."
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/treza-labs-text-to-speech-elevenlabs-db39a596/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from www.trezalabs.com](https://www.zero.xyz/host/www.trezalabs.com/llms.txt)