​
Before You Begin

Before you begin, ensure you have a CAMB.AI account and have created an API key. You can find your API key in your CAMB.AI workspace API Keys dashboard. If you don’t have an account, you can sign up for one at CAMB.AI Studio.

​
Authentication

All API requests require authentication using your unique API key. You’ll need to include this key in the header of every request you make to any endpoint in CAMB.AI APIs. 
headers = {
    "x-api-key": "your_api_key_here",
    "Accept": "application/json"
}

​
API Key Management

Your API key is available from your CAMB.AI workspace API Keys dashboard. Remember to keep this key secure and never expose it in client-side code.

​
Understanding Resource Usage

All API calls share a common quota based on your subscription plan. Resources are consumed based on:
  • Characters processed (for TTS, Translated TTS, Audio Separation, Transaled Stories and Translation).
  • Minutes of media processed/generated (for Dubbing, Stories and Text To Sound).

​
Working with Languages and Voices

​
Discovering Available Languages

Before using our translation or speech services, you’ll want to know which languages are supported: 
import requests
import json

headers = {
    "x-api-key": "your_api_key_here",
    "Accept": "application/json"
}

print("Fetching available source languages...")
# Getting source languages
response = requests.get(
    "https://client.camb.ai/apis/source-languages",
    headers=headers
)
source_languages = response.json()
print(f"Retrieved {len(source_languages)} source languages")
print("First 3 languages:", json.dumps(source_languages[:3], indent=2))

print("\nFetching available target languages...")
# Getting target languages
response = requests.get(
    "https://client.camb.ai/apis/target-languages",
    headers=headers
)
target_languages = response.json()
print(f"Retrieved {len(target_languages)} target languages")
print("First 3 languages:", json.dumps(target_languages[:3], indent=2))

​
Exploring Available Voices

Each voice in our system has unique characteristics. Browse available voices with: 
import requests
import json

headers = {
    "x-api-key": "your_api_key_here",
    "Accept": "application/json"
}

print("Fetching available voice options...")
response = requests.get(
    "https://client.camb.ai/apis/list-voices",
    headers=headers
)
voices = response.json()
print(f"Retrieved {len(voices)} voices")

# Display some sample voice information
if voices and len(voices) > 0):
    sample_voice = voices[0]
    print(f"Sample voice details: {json.dumps(sample_voice, indent=2)}")

​
Asynchronous Operations

Many of our APIs perform complex processing that takes time to complete. These operations follow an asynchronous pattern:
  1. Submit a request and receive a task_id.
  2. Poll the task status using the task_id.
  3. Once complete, retrieve results using the run_id.
This pattern is consistent across our non-Streaming APIs.

​
Next Steps

Ready to dive deeper? Continue exploring our detailed documentation for each API:

Text-to-Speech

Transform text into natural-sounding speech with customizable voice parameters for age, gender, and emotion across 140+ languages

Dubbing

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

Stories

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

Translation

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

Transcription

Convert speech to highly accurate text with speaker identification, timestamps, and specialized terminology support.

Voice from Description

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

Text-to-Sound

Generate realistic soundscapes and audio environments from text descriptions for immersive experiences without traditional production constraints.

Audio Separation

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