Skip to main content
CAMB.AI is the localization AI infrastructure company built to help the world’s biggest Enterprises reach 8 billion fans, customers and viewers. Supporting 140+ languages! Explore our docs to integrate Camb AI’s MARS & BOLI models into your applications.

SDK Guide

Learn how to install and use the Python & Node.js SDKs to build voice apps quickly.

Custom Cloud Providers

Access MARS models on your own favorite cloud providers like Google Cloud, Modal, Baseten, etc.

Open Source

Explore our open-source models MARS 6 and MARS 5 on GitHub.

​
Features Suite

  • Live Text to Speech: Realistic, emotional speech synthesis, featuring MARS 8 in 4 variants - mars pro, mars flash, mars instruct, and mars nano. Available on all cloud providers.
  • Translation: Context-aware neural translation using our proprietary BOLI Model.
  • Dubbing: Automated video dubbing using our AI that preserves emotional delivery across 140+ languages.
  • Voice Cloning: Create digital voice replicas from audio as short as 2 seconds.
  • Audio Separation: Isolate and extract distinct audio components from mixed recordings using deep learning to separate speech from background elements.
  • Sound and Music: Create high-quality music and realistic soundscapes, delivering immersive audio experiences from simple text prompts.
  • Transcription: Convert speech to text with speaker identification, timestamps, and specialized terminology (dictionaries) support. and more!
Continue exploring our detailed documentation for each API:

Text-to-Speech

Transform text into natural-sounding speech with customizable voice features across 140+ languages

Translated Text-to-Speech

Translate text and synthesize speech in one step across 140+ languages

Dubbing

Localize your content using our AI that preserves emotional delivery across 140+ languages

Stories

Convert written narratives into audiobooks using your own voice or custom voice.

Translated Stories

Translate and convert narratives into audiobooks in 140+ languages

Translation

Translate content across 140+ language pairs with context-aware neural technology.

Transcription

Convert speech to text with speaker identification, timestamps, and specialized terminology (dictionaries) support.

Voice from Description

Create unique voices by describing characteristics or clone existing voices from audio samples for consistent brand identity.

Sound and Music

Create high-quality music and realistic soundscapes, delivering immersive audio experiences from simple text prompts.

Audio Separation

Isolate and extract distinct audio components from mixed recordings using deep learning to separate speech from background elements.