Daily (Pipecat)
Pipecat is an open source Python framework for building real-time voice and multimodal AI agents that can see, hear, and speak. It’s designed for developers who want full control over how AI services, network transports, and audio processing are orchestrated—enabling ultra-low latency, natural-feeling conversations across custom pipelines, whether running locally or in production infrastructure. Inworld voices and text-to-speech models are supported via a built-inInworldTTSService, allowing you to stream high-quality audio or generate speech on demand from within your own runtime.
To get started with Pipecat + Inworld, follow this guide.