Cartesia is a real-time voice AI platform offering low-latency text-to-speech, speech-to-text, and production voice agents in 44 languages via one API.
About
Cartesia is a voice AI company that builds real-time speech models and voice agents designed for live conversation. Its products address the core challenge of interactive voice applications: latency. Speech that arrives too slowly breaks the natural rhythm of a call, so Cartesia engineers its stack around speed without sacrificing accuracy.
The platform combines three main products accessible through a single API: Sonic, a text-to-speech model; Ink, a streaming speech-to-text model; and Managed Agents, a platform for building and deploying voice agents that can answer and place phone calls. All of these run on state space model (SSM) architectures, a research direction the company's team has contributed to through work on Mamba and H-Nets. Cartesia supports 44 languages and offers deployment across cloud, on-premise, and on-device environments, with in-region inference for organizations that must meet data residency and compliance requirements.
Key Features
Pricing & Fees
- Pricing: Plans start with a Free tier ($0/month, 20K credits, $1 in prepaid agent usage), Pro at $5/month (100K credits, commercial use license), Startup at $49/month (1.25M credits), Scale at $299/month (8M credits), and a custom Enterprise plan with volume pricing.
- Usage-based agent calls: Voice agent call duration is billed at $0.06 per minute, with telephony at $0.014 per minute when using a Cartesia-provided phone number.
- Free tier availability: The Free plan includes both text-to-speech and speech-to-text access, making it possible to test the API before paying.
- Separate concurrency pools: Text-to-speech, speech-to-text, and voice agent services each have dedicated concurrency limits, so heavy use of one does not reduce capacity for the others.
Who It's For
Cartesia targets developers and product teams building interactive voice applications, particularly those where response time matters, such as phone-based customer service, outbound verification calls, and step-up authentication in financial services. Enterprise teams in healthcare, government, retail, and travel can use its voice agents for inbound and outbound calling. Localization and content teams can use the multilingual text-to-speech for dubbing and voiceover work, while startups get an entry-level plan and commercial licensing at low monthly cost. Organizations with strict compliance needs can choose on-premise or on-device deployment.
FAQ
What is Cartesia?Cartesia is a voice AI platform providing real-time text-to-speech (Sonic), speech-to-text (Ink), and managed voice agents, all available through one API and supporting 44 languages.
Does Cartesia have a free plan?Yes. The Free plan costs $0 per month and includes 20,000 credits plus $1 of prepaid agent usage, with paid plans starting at $5 per month.
Where can Cartesia's models be deployed?The same models and agents can run in the cloud through regional API endpoints, on-premise, or on-device, with in-region inference to satisfy latency, data residency, and compliance needs.
How much do Cartesia voice agent calls cost?Call duration is billed at $0.06 per minute, and telephony costs $0.014 per minute when using a Cartesia-provided phone number on standard plans.
What research is Cartesia built on?The company's team has worked on state space model architectures, including Mamba and H-Nets, which underpin its low-latency speech models.
Related Tutorials
View all →
Related Tools
View all →
Speechify Speechify is a text-to-speech and voice AI app that reads PDFs, documents, and web pages aloud and turns speech into text across all major devices. 
AI Translator - Accurate Translation AI Translator provides high-accuracy translations with 98% precision, supporting 1200+ AI models and 100+ languages. 
FunASR - End-to-End Speech Recognition Toolkit Industrial-grade speech recognition toolkit. 170x realtime on GPU, 50+ languages, speaker diarization, emotion detection, OpenAI-compatible API, vLLM acceleration, and agent integration. 
IBM Watson Text-to-Speech Convert text to natural speech using IBM Watson's API and SaaS. 
NaturalReader NaturalReader is an AI text-to-speech platform that converts documents, webpages and scanned text into natural-sounding audio for personal, commercial and educational use.