Quick First API Call

This guide walks you through making your first CAMB.AI API call to generate speech from text.

Prerequisites

A CAMB.AI account (sign up at studio.camb.ai)
Your API key (see Authentication)

Option 1: Using the SDK (Recommended)

Install the SDK

pip install camb-sdk

npm install @camb-ai/sdk

Generate Speech

from camb.client import CambAI

client = CambAI(api_key="YOUR_API_KEY")

# Generate speech
audio = client.tts.generate(
    text="Hello! Welcome to CAMB AI.",
    voice_id=147320
)

# Save to file
with open("output.wav", "wb") as f:
    f.write(audio)

print("Audio saved to output.wav")

import { CambClient, saveStreamToFile } from '@camb-ai/sdk';

const client = new CambClient({ apiKey: "YOUR_API_KEY" });

// Generate speech
const response = await client.textToSpeech.tts({
   text: 'Welcome to our service. We\'re glad to have you here.',
    voice_id: 147320,
    language: 'en-us',
    speech_model: 'mars-8.1-flash-beta',
    output_configuration: { format: 'wav' }
});

// Save to file
await saveStreamToFile(response, "output.wav");

console.log("Audio saved to output.wav");

Play the Audio

Open output.wav with any audio player to hear the generated speech.

Option 2: Using cURL

curl -X POST "https://client.camb.ai/apis/tts-stream" \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Hello! Welcome to CAMB AI.",
    "voice_id": 147320,
    "language": "en-us",
    "speech_model": "mars-8.1-flash-beta"
  }' \
  --output output.wav

Option 3: Using the API Directly

import requests

response = requests.post(
    "https://client.camb.ai/apis/tts-stream",
    headers={
        "x-api-key": "YOUR_API_KEY",
        "Content-Type": "application/json"
    },
    json={
        "text": "Hello! Welcome to CAMB AI.",
        "voice_id": 147320,
        "language": "en-us",
        "speech_model": "mars-8.1-flash-beta"
    }
)

with open("output.wav", "wb") as f:
    f.write(response.content)

const response = await fetch("https://client.camb.ai/apis/tts-stream", {
  method: "POST",
  headers: {
    "x-api-key": "YOUR_API_KEY",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    text: "Hello! Welcome to CAMB AI.",
    voice_id: 147320,
    language: "en-us",
    speech_model: "mars-8.1-flash-beta"
  })
});

const audioData = await response.arrayBuffer();

Understanding the Response

The API returns raw audio data by default. Key parameters:

Parameter	Description
`text`	The text to convert to speech
`voice_id`	ID of the voice to use (147320 is a default English voice)
`language`	Language code (e.g., `en-us`, `es-es`, `fr-fr`)
`speech_model`	Model variant: `mars-8.1-flash-beta`, `mars-8.1-pro-beta`, `mars-flash`, `mars-pro`, or `mars-instruct`

Output Formats

Specify the output format in output_configuration:

{
  "output_configuration": {
    "format": "wav"  // Options: "pcm_s16le", "wav", "mp3"
  }
}

Explore Voices

List available voices to find the right one for your use case:

curl -X GET "https://client.camb.ai/apis/list-voices" \
  -H "x-api-key: YOUR_API_KEY"

Next Steps

How Tasks & Runs Work

Understand the async task pattern

SDK Guide

Deep dive into SDK features

MARS 8 Models

Compare TTS model variants

API Reference

Explore all endpoints

Getting Started

Models

Tutorials

SDK Guides

Hosting Platforms

Integrations

API Reference

Other Products

Release Logs

Quick First API Call

Prerequisites

Option 1: Using the SDK (Recommended)

Option 2: Using cURL

Option 3: Using the API Directly

Understanding the Response

Output Formats

Explore Voices

Next Steps

How Tasks & Runs Work

SDK Guide

MARS 8 Models

API Reference

​Prerequisites

​Option 1: Using the SDK (Recommended)

​Option 2: Using cURL

​Option 3: Using the API Directly

​Understanding the Response

​Output Formats

​Explore Voices

​Next Steps

How Tasks & Runs Work

SDK Guide

MARS 8 Models

API Reference

Prerequisites

Option 1: Using the SDK (Recommended)

Option 2: Using cURL

Option 3: Using the API Directly

Understanding the Response

Output Formats

Explore Voices

Next Steps