Cartesia
Cartesia offers real-time speech generation, transcription and voice agent models built on state space models, accessed through a single API.
About this tool
Cartesia builds real-time voice AI models for developers. A single API provides speech synthesis, live transcription and voice agents with latency low enough for real-time conversation. The company’s models are built on state space models, an architecture it presents as enabling low latency, long-context reasoning and efficiency at scale.
Customers use Cartesia for voice agents in areas such as financial services, for example outbound verification calls about suspicious transactions. Pricing gives each plan a monthly pool of credits for text-to-speech and transcription plus prepaid dollars for managed agents, and each service has its own concurrency pool so they do not compete for capacity.
What you can do
Text-to-speech
Low-latency speech generation designed for live, interactive applications.
Streaming transcription
Real-time speech-to-text for conversations and agents.
Managed voice agents
Deploy production voice agents billed per minute from prepaid balances.
Separate concurrency pools
TTS, STT and agents each have dedicated capacity.
Who is it for?
- A bank places automated verification calls about unusual card activity.
- A developer adds a real-time voice to a conversational app.
- A contact centre transcribes calls live for agent assistance.
Before you choose
Leaderboard rankings cited on the site are snapshots; test voices and latency on your own use case.
Credit-based pricing differs between TTS, STT and agents, so model your mix before choosing a plan.
Frequently asked questions
What makes Cartesia’s models different?
Cartesia builds its models on state space models, an architecture it says delivers low latency and efficient long-context processing.
Does Cartesia have a free plan?
Yes. The free plan includes 20,000 credits per month for voice models and $1 of prepaid agent usage.
How much do Cartesia voice agents cost?
Cartesia quotes about $0.06 per minute for managed voice agents, drawn from prepaid amounts included in each plan.
Check the official website for current features, pricing, and terms.
Similar tools
AssemblyAI
AudioAssemblyAI offers speech-to-text and voice AI APIs, including its Universal speech models, streaming transcription, speech understanding and a voice agent API.
Deepgram
AudioDeepgram provides speech-to-text and text-to-speech APIs for developers, including Nova transcription models and Flux models built for voice agents.
Google AI Studio
CodingGoogle AI Studio is Google’s web workspace for testing Gemini models, getting a Gemini API key, building prototypes and moving them into production.
Retell AI
AutomationRetell AI is a platform for building, testing and deploying AI voice agents that handle phone calls, with pay-as-you-go pricing and low-latency conversation.
Vapi
AutomationVapi is a developer platform for building voice AI agents that handle phone and web calls, combining speech recognition, an LLM and speech synthesis.
Groq
CodingGroq is an inference cloud built around its own LPU chips, offering fast, OpenAI-compatible API access to open AI models for developers and enterprises.