Vapi chooses Cartesia as their default provider for voice agents

“One of our healthcare customers reported that their patients were 4x more likely to stay on a call after switching to Cartesia's voices compared to their previous text-to-speech provider.”

— Nikhil Gupta, Vapi CTO

Vapi enables anyone to build, test, and deploy high quality conversational voice agents in minutes. As one of Cartesia's earliest design partners, they identified a market gap for a low-latency, developer-first audio platform to power conversational voice agents. Vapi has one of the fastest and highest-quality conversational platforms on the market, and we're proud that after integrating with every major TTS provider, they’ve chosen us to be their default model provider and to power their homepage demo (try chatting with Vapi below!)

For conversational agent providers like Vapi, 3 things matter most in selecting a TTS provider:

• Industry-Leading Latency: Cartesia is the only provider with end-to-end latency consistently under 200 ms across all languages. This enables response times that match the natural pacing of human conversation.

• Realistic Voices: Cartesia’s voices are nearly indistinguishable from human speech. The library features voices with a conversational tone with natural pausing and intonation learned from the context of the audio.

• Accurate Pronunciation: Cartesia nails the pronunciation of challenging content such as acronyms, phone numbers, and rare words. It also supports IPA (International Phonetic Alphabet) for specialized use cases such as prescription drug names in the healthcare sector.

“Vapi was one of our earliest design partners. We were thrilled to collaborate with them as they are experts in building conversational voice agents and understand the intricacies of every existing text-to-speech provider. We couldn't have asked for a better team to help us develop the best purpose-built solution for real-time conversation.”

— Karan Goel, Cartesia CEO