camb

Integrate CAMB AI speech APIs for TTS, voice cloning, translation, transcription, and dubbing.

Updated Feb 6, 2026
One-click install
npx skills add https://github.com/Camb-ai/agent-skill --skill camb
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: camb
Source: https://github.com/Camb-ai/agent-skill/tree/main/skills/camb
Command: npx skills add https://github.com/Camb-ai/agent-skill --skill camb

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

CAMB AI provides a suite of speech APIs (TTS, voice cloning, dubbing, translation, and transcription) that let developers embed high-quality voice and language capabilities into applications without building them from scratch.

Core Features & Use Cases

  • Text-to-Speech (TTS): Real-time or streaming speech in multiple languages and voices.
  • Voice Cloning & Dubbing: Create custom voices from short references and dub content in foreign languages.
  • Translation & Transcription: Translate text to multiple languages and transcribe audio for multilingual workflows.
  • Use Case: Build multilingual virtual assistants, voice-enabled apps, or automated media localization pipelines.

Quick Start

Install the camb-sdk (Python or Node.js), set CAMB_API_KEY, and run a basic example to generate speech from sample text. For more advanced workflows, explore the REST endpoints listed in the REST API Reference and the provided examples.

Frequently Asked Questions about camb

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I integrate voice cloning and TTS APIs into my application?

You can integrate voice cloning and TTS APIs by installing the camb-sdk in Python or Node.js, setting your CAMB_API_KEY, and calling the REST endpoints to generate speech from text or short voice references.

Can I use CAMB AI APIs for automated media dubbing in foreign languages?

Yes, CAMB AI APIs support automated media dubbing by allowing you to create custom voices from short references and generate dubbed audio in foreign languages through the provided SDKs or REST endpoints.

What is the best way to build a multilingual virtual assistant with real-time streaming speech?

The best way to build a multilingual virtual assistant is using CAMB AI's real-time streaming TTS and translation APIs, which handle multilingual speech generation and playback directly within your application workflows.

Do I need a specific SDK to perform audio transcription and translation workflows?

You need the camb-sdk available in Python or Node.js, along with a valid CAMB_API_KEY, to access the REST endpoints for transcribing audio and translating text across multiple languages.

Does CAMB AI support multilingual translation playback for voice-enabled apps?

CAMB AI supports multilingual translation playback by combining its translation and TTS APIs, enabling voice-enabled apps to translate text into multiple languages and stream the synthesized speech in real time.