Skip to main content
Get started with the Camb.ai Rust SDK in minutes

​
Overview

The Camb.ai Rust SDK provides a simple interface to integrate high-quality text-to-speech into your applications. This quickstart will have you generating speech in under 5 minutes.

​
Installation

Add the following to your Cargo.toml: 
[dependencies]
camb_api = { git = "https://github.com/Camb-ai/cambai-rust-sdk" }
tokio = { version = "1.0", features = ["full"] }
futures = "0.3"

​
Authentication

Get your API key from CAMB.AI Studio and set it as an environment variable: 
export CAMB_API_KEY=your_api_key_here

​
Quick Start

​
Streaming Text-to-Speech

Generate and stream speech in real-time. The SDK uses tokio for async and returns a stream of bytes: 
use camb_api::prelude::*;
use std::io::Write;
use futures::stream::TryStreamExt;

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    // Initialize the client
    let client = APIClient::new(ClientConfig {
        api_key: Some(std::env::var("CAMB_API_KEY")?),
        ..ClientConfig::default()
    })?;

    // Stream TTS audio
    let mut stream = client.text_to_speech.tts(&CreateStreamTtsRequestPayload {
        text: "Hello! Welcome to Camb.ai text-to-speech.".to_string(),
        language: CreateStreamTtsRequestPayloadLanguage::EnUs,
        voice_id: 147320,
        speech_model: Some(CreateStreamTtsRequestPayloadSpeechModel::MarsFlash),
        output_configuration: Some(StreamTtsOutputConfiguration {
            format: Some(OutputFormat::Wav),
            ..Default::default()
        }),
        ..Default::default()
    }, None).await?;

    // Save to file
    let mut file = std::fs::File::create("output.wav")?;
    while let Some(chunk) = stream.try_next().await? {
        file.write_all(&chunk)?;
    }

    println!("Success! Audio saved to output.wav");
    Ok(())
}

​
Using the Helper Function

You can easily wrap the stream processor into a helper function: 
use futures::stream::TryStreamExt;
use std::io::Write;

async fn save_stream_to_file<S, E>(mut stream: S, path: &str) -> Result<(), Box<dyn std::error::Error>>
where
    S: futures::Stream<Item = Result<Vec<u8>, E>> + Unpin,
    E: std::error::Error + Send + Sync + 'static,
{
    let mut file = std::fs::File::create(path)?;
    while let Some(chunk) = stream.try_next().await? {
        file.write_all(&chunk)?;
    }
    Ok(())
}

// Usage:
let stream = client.text_to_speech.tts(&payload, None).await?;
save_stream_to_file(stream, "output.wav").await?;

​
Choosing a Model

Camb.ai offers three MARS models optimized for different use cases: 
speech_model: Some(CreateStreamTtsRequestPayloadSpeechModel::MarsFlash)
// Best for: Real-time voice agents, low-latency applications
// Sample rate: 22.05kHz

​
Listing Available Voices

Discover available voices for your application: 
let voices = client.voice_cloning.list_voices(&ListVoicesListVoicesGetRequest::default(), None).await?;

for voice in voices {
    println!("ID: {}, Name: {}, Gender: {:?}", voice.id, voice.voice_name, voice.gender);
}

​
Language Support

Camb.ai supports 140+ languages. Specify the language using the CreateStreamTtsRequestPayloadLanguage enum: Languages supported by each model mentioned at MARS Models. 
// English (US)
language: CreateStreamTtsRequestPayloadLanguage::EnUs

// Spanish
language: CreateStreamTtsRequestPayloadLanguage::EsEs

// French
language: CreateStreamTtsRequestPayloadLanguage::FrFr

​
Error Handling

Handle common errors gracefully: 
match client.text_to_speech.tts(&payload, None).await {
    Ok(stream) => { /* Process stream */ },
    Err(e) => println!("Error generating speech: {}", e),
}

​
Using Custom Provider

For more details check this guide Custom Cloud Providers

​
Baseten Deployment

Initialize the client with your API key and the specific model URL. Baseten Provider Example 
use camb_api::provider::BasetenProvider;

let tts_provider = BasetenProvider::new(
    "YOUR_BASETEN_API_KEY".to_string(),
    Some("YOUR_BASETEN_URL".to_string()),
);

​
Next Steps

https://mintcdn.com/cambai/2LvnefIkletroPxv/images/pipecat-orange.svg?fit=max&auto=format&n=2LvnefIkletroPxv&q=85&s=40cf8e001b8cadc8a4c3c557dea603d5

Voice Agents

Build real-time voice agents with Pipecat
https://mintcdn.com/cambai/2LvnefIkletroPxv/images/livekit-orange.svg?fit=max&auto=format&n=2LvnefIkletroPxv&q=85&s=c750fcee9b1de69e3c1d0d6ec7eb6b3f

LiveKit Integration

Create voice agents with LiveKit

API Reference

Explore the full TTS API

Voice Library

Browse available voices

​
Resources