Zekron Voice

Human-like neural text-to-speech with multiple voices and languages, including Tajik, Russian and English. Adjustable speed and pitch.

Back to docs

Audiozekron/voice$0.015 per 1K charsmax prompt 5,000 chars

Supported modes

tts

Parameters

Pass these inside the input object when creating a task.

Field	Required
text	required
voice	optional
language	optional
speed	optional
format	optional

Example request

bash

curl -X POST https://api.zekron.tech/api/v1/task \
  -H "Authorization: Bearer zk_live_xxx" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "zekron/voice",
  "input": {
    "text": "Welcome to ZekronAI, your unified generation API.",
    "voice": "aria"
  }
}'

Example response

json

{
  "id": "zk_task_8f3a2b1c9d",
  "model": "zekron/voice",
  "status": "succeeded",
  "output": {
    "audio": "https://cdn.zekron.tech/out/zk_task_8f3a2b1c9d.mp3"
  },
  "cost_usd": 0.015,
  "created_at": "2026-06-10T12:00:00Z",
  "completed_at": "2026-06-10T12:00:42Z"
}

Pricing

This model is billed at $0.015 per 1K chars. You are only charged for successful generations — failed tasks are never billed. Generated outputs are retained for 21 days before they expire.