elevenlabs_ttv

A type-safe, async Rust client for the ElevenLabs Text To Voice API. Design a voice via a prompt with simple, Ergonomic API.

Features

• Type-safe & Async: Built with Rust's type system and async/await support
• Builder Pattern: Intuitive, chainable API for configuring TTV requests
• Model Support: Full support for ElevenLabs models (models::elevenlabs_models::*)
• Customizable: Elevanlabs TTV APIs, custom base URLs, and enterprise support
• Tokio Ready: Works seamlessly with the Tokio runtime

Check-out Also:

This project is part of a milestone to implement all ElevenLabs APIs in Rust.

• Elevenlabs TTS: ElevenLabs Text-to-Speech API. ✅
• Elevenlabs STT: ElevenLabs Speech-to-Text API. ✅
• Elevenlabs TTD: ElevenLabs Text-to-Dialogue API. ✅
• Elevenlabs TTV: ElevenLabs Text-to-Voice API. ✅
• Elevenlabs TTM: ElevenLabs Text-to-Music API. ✅
• Elevenlabs SFX: ElevenLabs Sound Effects API. ✅
• Elevenlabs VC: ElevenLabs Voice Changer API. ✅
• Elevenlabs AUI: ElevenLabs Audio Isolation API. ⏳
• Elevenlabs DUB: ElevenLabs Dubbing API. ⏳

Installation

Add this to your Cargo.toml:

[dependencies]
elevenlabs_ttv = "0.0.3"

Quick Start

use elevenlabs_ttv::{ElevenLabsTTVClient, voices};

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let client = ElevenLabsTTVClient::new("your-api-key");

    let voice_description =
        "Smooth, elegant female, 30s, soft French accent, refined and sophisticated.";

    let designed_voice = client.design_voice(voice_description).execute().await?;
    let designed_voice_id = designed_voice
        .previews
        .first()
        .unwrap()
        .generated_voice_id
        .clone();

    println!("Designed Voice Results {:?}", designed_voice);

    let created_voice = client
        .create_voice("Elina", voice_description, &designed_voice_id)
        .execute()
        .await?;

    println!("Created Voice Results {:?}", created_voice);

    Ok(())
}

Examples

Basic Usage

use elevenlabs_ttv::{ElevenLabsTTVClient, voices};
use std::env;

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
     let api_key =
        env::var("ELEVENLABS_API_KEY").expect("Please set ELEVENLABS_API_KEY environment variable");

    let client = ElevenLabsTTVClient::new(api_key);

    let voice_description =
        "Smooth, elegant female, 30s, soft French accent, refined and sophisticated.";

    let designed_voice = client.design_voice(voice_description).execute().await?;
    let designed_voice_id = designed_voice
        .previews
        .first()
        .unwrap()
        .generated_voice_id
        .clone();

    println!("Designed Voice Results {:?}", designed_voice);

    let created_voice = client
        .create_voice("Elina", voice_description, &designed_voice_id)
        .execute()
        .await?;

    println!("Created Voice Results {:?}", created_voice);

    Ok(())
}

Advanced Configuration

use elevenlabs_ttv::{ElevenLabsTTVClient, VoiceSettings, models, voices};
use std::env;

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let api_key =
        env::var("ELEVENLABS_API_KEY").expect("Please set ELEVENLABS_API_KEY environment variable");

    let client = ElevenLabsTTVClient::new(api_key);

    let voice_description =
        "Bright, energetic female, early 20s, Californian accent, playful and fast-paced.";
    let voice_text =
        "Hi! I’m your smart creative assistant. Tell me what you want to make, and I’ll help you design it—step by step. Ready when you are."

    let designed_voice = client
        .design_voice(voice_description)
        .model(models::elevanlabs_models::ELEVEN_MULTILINGUAL_TTV_V2)
        .text(voice_text)
        .auto_generate_text(true)
        .loudness(1.0)
        .guidance_scale(20)
        .quality(1.0)
        .execute()
        .await?;
    let designed_voice_id = designed_voice
        .previews
        .first()
        .unwrap()
        .generated_voice_id
        .clone();

    println!("Designed Voice Results {:?}", designed_voice);

    let created_voice = client
        .create_voice("Andrea", voice_description, &designed_voice_id)
        .execute()
        .await?;

    println!("Created Voice Results {:?}", created_voice);

    Ok(())
}

Running Examples

# Set your API key
export ELEVENLABS_API_KEY=your_api_key_here

# Run the basic example
cargo run --example basic_ttv

# Run the advanced example
cargo run --example advanced_ttv

API Overview

Error Handling

The crate uses standard Rust error handling patterns. All async methods return Result types:

match client.design_voice(voice_description).execute().await {
    Ok(output) => println!("Designed voice results: {:?}", output),
    Err(e) => eprintln!("TTV request failed: {}", e),
}

Requirements

• Rust 1.70+ (for async/await support)
• Tokio runtime
• Valid ElevenLabs API key

License

Licensed under either of:

• MIT License
• Apache License, Version 2.0

at your option.

Contributing

Contributions are welcome! Please feel free to:

• Open issues for bugs or feature requests
• Submit pull requests with improvements
• Improve documentation or examples
• Add tests or benchmarks

Before contributing, please ensure your code follows Rust conventions and includes appropriate tests.

Support

If you like this project, consider supporting me on Patreon 💖

Changelog

See CHANGELOG.md for a detailed history of changes.

Note: This crate is not officially affiliated with ElevenLabs. Please refer to the ElevenLabs API documentation for the most up-to-date API information.