User Guide API Reference

Introduction

Welcome to the Moknah AI Audio Platform

Overview

Moknah is a comprehensive AI audio platform that converts text into lifelike audio, featuring nuanced intonation, pacing, and emotional awareness. Beyond generation, Moknah empowers your entire workflow with speech-to-text for accurate transcription, automated Video Dubbing, Voice Cloning, and a dedicated Studio for long-form projects.

Whether you are creating content or converting it, our models adapt to your needs across multiple languages and voice styles.

Moknah Platform Overview

Core Capabilities

  • Narrate global media campaigns & ads — Create professional voiceovers for marketing content worldwide
  • Produce audiobooks — Multiple languages with complex emotional delivery
  • Dubbing — Translate content across languages while preserving original voice characteristics
  • Voice Cloning — Create digital replicas of voices with high fidelity

Supported Output Formats

The default response format is mp3 with the following specifications:

Format Bitrate Sample Rate Available Via
MP3 128 kbps 44.1 kHz Studio & API
MP3 192 kbps 44.1 kHz Studio & API
Ready to Get Started?

Head over to Text to Speech to learn how to generate your first audio.