# Cartesia

Add Cartesia text-to-speech to Bolna voice agents for ultra-fast, natural sounding voice output. Built from the ground up for real-time phone conversations.

[Official Documentation](https://docs.cartesia.ai/)

## How Cartesia fits in the stack

### Best for
Natural delivery, tone, and response speed on live calls.

### Use this layer when
You care about voice quality, expressiveness, or low-latency playback.

### Connects to
LLM output upstream and the phone network downstream.

## Text-to-speech is the speaking layer

This provider turns the agent’s response into audio the caller hears. It affects brand perception, caller comfort, and how quickly the next utterance can begin.

**Telephony**  
**Phone Network**  
→  
**STT**  
**Listener**  
→  
**LLM**  
**Reasoning**  
→  
**TTS**  
**Voice**  
→  
**Tools**  
**Actions**

This page focuses on where Cartesia fits in a production voice stack. For full setup steps, credentials, and API details, use the documentation link above.

# Overview

Cartesia delivers low latency text-to-speech that is made for real-time voice applications. With Bolna's Cartesia integration, you can build voice agents with near-instantaneous speech synthesis, creating natural, flowing conversations without visible delays.

Cartesia's TTS achieves sub-300ms latency from text input to audio output, which is critical for maintaining natural conversation rhythm where even small delays can feel awkward to callers.

## Features & Use Cases

**Ultra-Fast Responses (Under 300ms)**  
Cartesia generates speech in less than 300 milliseconds. This removes awkward pauses and keeps conversations flowing naturally.

**Real-Time Audio Streaming**  
Audio plays as it is being created. This lets voice agents start talking even before the whole sentence is ready, making interactions feel instant and real.

**Natural, Human-Like Voices**  
Even though it's incredibly fast, Cartesia sounds like a real person with natural tone, emotion, and rhythm.

**Lots of Voice Choices**  
Pick from a wide variety of voices, accents, and styles to perfectly match your brand.

**Built for Phone Calls**  
Optimized specifically for real-time voice applications like phone calls, ensuring smooth and delay-free conversations.

**Use Case: Fast-Paced Customer Support**  
Perfect for busy customer service calls where quick, clear answers keep customers happy and help resolve issues faster.

**Use Case: Financial Services & Trading**  
Ideal for high stakes trading or banking support where every second matters and delays cause frustration.

**Use Case: Urgent Response Lines**  
Great for emergency or urgent situations where fast communication is needed to deliver critical information immediately.

## Other providers in this layer

- [Synthesizer **ElevenLabs**](/content/integrations/elevenlabs/index.html)  
  Give your Bolna voice agents lifelike speech with ElevenLabs. Clone a custom voice or pick from a large library of expressive, natural sounding options.
- [Synthesizer **Rime**](/content/integrations/rime/index.html)  
 Use Rime neural speech synthesis with Bolna voice agents for expressive, natural sounding voices. High quality TTS that makes phone conversations engaging.
- [Synthesizer **Sarvam AI (TTS)**](/content/integrations/sarvam-tts/index.html)  
 Full Indian language AI stack for Bolna voice agents. LLM, speech-to-text, and text-to-speech tuned for Hindi, Tamil, Telugu, Kannada, and 10+ languages.

## See where Cartesia fits in your production workflow

Use the demo to walk through provider selection, stack tradeoffs, and the exact workflow you want Bolna to automate.