Pipecat - Cartesia Docs

Pipecat is an open-source Python framework for realtime voice and multimodal agents (pipelines, transports such as Daily or LiveKit, pluggable AI services). Cartesia ships as first-party TTS and STT services in the Pipecat repo. Pipecat’s examples assume a recent Python (see the Pipecat repo; 3.11+ is typical for current stacks). Enable the Cartesia and transport extras the upstream README calls out for the example you run. Pipecat’s getting-started examples are built on Cartesia’s WebSocket API, so they are the natural first place to try Cartesia:

Pipecat > Examples > Getting Started

Getting-started examples in the Pipecat repo.

For a fuller sample app, see StudyPal:

Pipecat > Examples > StudyPal

StudyPal example in the pipecat-examples repo.

For smaller voice-focused samples in the main repo, Cartesia STT and TTS are wired up in two variants (WebSocket TTS and HTTP TTS):

Pipecat > Examples > Voice (Cartesia, WebSocket)

Voice bot using Cartesia WebSocket TTS.

Pipecat > Examples > Voice (Cartesia, HTTP)

Same flow using Cartesia HTTP TTS.

⌘I