ElevenLabs API: eleven_v4 speech synthesis, voice ID and MP3 checks

Models and current API429 rates

These are exact speech model IDs for this family. The public catalog and GET /v1/models for your key answer different questions: a published entry does not prove account access. Preserve hyphens, dots and versions exactly.

Catalog data date: Oct 25, 2026, 8:27 AM UTC. Rates retain their catalog conditions; an absent row does not mean a free request.

Family pricing and calculator · Full catalog

Choose your next connection step

• ElevenLabs API pricing

  Compare character billing units, workload budgets and published rate conditions for ElevenLabs speech synthesis.

• API429 model catalog

  Check the literal eleven_v4 catalog entry, audio capabilities and live tts_characters billing units.

• API429 quickstart

  Set up your API429 key, verify model access in GET /v1/models and review documented endpoint contracts.

First speech synthesis: curl, Python, JavaScript

1. Create a key in your API429 account and add balance by Russian bank card, a business invoice, USDT or TON. A $10 test balance is available for subscribing to the Telegram channel through the bonus bot.
2. Use the same key to verify eleven_v4 in GET https://gateway.api429.com/v1/models.
3. Set API429_API_KEY on the server and send a small paid request. The example does not retry automatically.
4. Inspect HTTP status, MP3 MIME type and a non-empty response body, then listen to the saved file. A timeout does not prove that the operation was unbilled.

The request uses POST /v1/audio/speech, an explicit voice and response_format=mp3. Set a confirmed API429_VOICE_ID for Python and JavaScript; replace YOUR_VOICE_ID in curl. No default voice is assumed. Python and JavaScript verify key access, audio MIME type and a non-empty body; for curl, check the model list and response separately before saving the MP3.

curl

curl --fail-with-body https://gateway.api429.com/v1/audio/speech \
  -H "Authorization: Bearer $API429_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"eleven_v4","input":"Welcome. Check the pronunciation and pacing of this short sample before running batch speech synthesis.","voice":"YOUR_VOICE_ID","response_format":"mp3"}' \
  --output speech.mp3

Python 3

import base64
import json
import os
import urllib.request
from pathlib import Path

key = os.environ["API429_API_KEY"]
base = "https://gateway.api429.com/v1"
headers = {"Authorization": "Bearer " + key, "Content-Type": "application/json"}
model = "eleven_v4"
with urllib.request.urlopen(urllib.request.Request(base + "/models", headers=headers), timeout=30) as response:
    available = {item["id"] for item in json.load(response)["data"]}
if model not in available:
    raise ValueError("Model unavailable to this key")
payload = json.loads("{\"model\":\"eleven_v4\",\"input\":\"Welcome. Check the pronunciation and pacing of this short sample before running batch speech synthesis.\",\"voice\":\"YOUR_VOICE_ID\",\"response_format\":\"mp3\"}")
payload["voice"] = os.environ["API429_VOICE_ID"]
if not payload["voice"] or payload["voice"] == "YOUR_VOICE_ID":
    raise ValueError("Set a confirmed voice ID")
request = urllib.request.Request(base + "/audio/speech",
    data=json.dumps(payload).encode("utf-8"), headers=headers, method="POST")
with urllib.request.urlopen(request, timeout=180) as response:
    content_type = response.headers.get("Content-Type", "").split(";")[0].strip().lower()
    if content_type not in ("audio/mpeg", "audio/mp3"):
        raise ValueError("Expected MP3 MIME; inspect response before saving")
    audio = response.read()
if not audio:
    raise ValueError("Empty audio")
Path("speech.mp3").write_bytes(audio)

JavaScript: Node.js 18+

import { writeFile } from "node:fs/promises";
const key = process.env.API429_API_KEY;
if (!key) throw new Error("Set API429_API_KEY");
const base = "https://gateway.api429.com/v1";
const headers = { Authorization: "Bearer " + key, "Content-Type": "application/json" };
const model = "eleven_v4";
const available = await fetch(base + "/models", { headers, signal: AbortSignal.timeout(30000) });
if (!available.ok) throw new Error("Models HTTP " + available.status);
if (!(await available.json()).data.some(item => item.id === model)) throw new Error("Model unavailable to this key");
const payload = {"model":"eleven_v4","input":"Welcome. Check the pronunciation and pacing of this short sample before running batch speech synthesis.","voice":"YOUR_VOICE_ID","response_format":"mp3"};
payload.voice = process.env.API429_VOICE_ID;
if (!payload.voice || payload.voice === "YOUR_VOICE_ID") throw new Error("Set a confirmed voice ID");
const response = await fetch(base + "/audio/speech", {
 method: "POST", headers, body: JSON.stringify(payload), signal: AbortSignal.timeout(180000)
});
if (!response.ok) throw new Error("Generation HTTP " + response.status);
if (!["audio/mpeg", "audio/mp3"].includes((response.headers.get("content-type") || "").split(";")[0].trim().toLowerCase())) throw new Error("Expected MP3 MIME");
const bytes = Buffer.from(await response.arrayBuffer());
if (!bytes.length) throw new Error("Empty audio");
await writeFile("speech.mp3", bytes);

These examples do not prove access for your key; verify the exact ID before a paid request. API contract · Configure your client · Questions and support

Frequently asked questions

Sources and editorial review

Manufacturer documentation describes its family and its own API rules. API429 IDs, rates and request contracts require separate catalog and documentation checks. The original source-review date below is retained; English publication does not renew the source review.

• ElevenLabs documentation: models overview
• ElevenLabs documentation: native text-to-speech convert reference
• API429 public catalog
• API429 public request contract

Source review: Oct 24, 2026, 12:34 PM UTC. To connect, create an API429 account and follow the quickstart instructions.