/api/x402/speechText 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.
{
"additionalProperties": false,
"properties": {
"async": {
"default": false,
"description": "true: answer at once, status running with a statusUrl.",
"type": "boolean"
},
"model": {
"default": "eleven-v3",
"enum": [
"eleven-v3",
"eleven-multilingual-v2"
],
"type": "string"
},
"text": {
"description": "What to say.",
"maxLength": 3000,
"type": "string"
},
"voice": {
"default": "george",
"description": "A voices[].id from GET on this URL, e.g. george, brian, alice.",
"type": "string"
}
},
"required": [
"text"
],
"type": "object"
}{
"audio": "https://www.trezalabs.com/api/media/generated/x402_speech/1a2b3c4d.mp3?s=...&c=...",
"characters": 84,
"model": "eleven-v3",
"paidUsd": 0.04,
"runId": "2026-09-23T18:04:11.000Z#1a2b3c4d",
"status": "success",
"statusUrl": "https://www.trezalabs.com/api/x402/speech?runId=...&token=...",
"transaction": "0x...",
"voice": "george"
}