- Add skip_tts as an init parameter for TextFrame, LLMFullResponseStartFrame, and LLMFullResponseEndFrame instead of setting it post-init - Update all LLM services to pass skip_tts when creating frames: - Anthropic, AWS (Bedrock, Nova Sonic, AgentCore), Google (Gemini, Gemini Live) - OpenAI (base, realtime), OpenAI Realtime Beta, SambaNova - Add _get_skip_tts() helper method in LLMService base class - Remove push_frame override that was setting skip_tts after frame creation
Pipecat Examples
This directory contains examples to help you learn how to build with Pipecat.
Getting Started
New to Pipecat? Start here:
- Quickstart - Get your first voice AI bot running in 5 minutes (coming soon)
- Client/Server Web - Learn to build web applications with Pipecat's client SDKs (coming soon)
- Phone Bot with Twilio - Connect your bot to a phone number (coming soon)
Foundational Examples
Single-file examples that introduce core Pipecat concepts one at a time. These examples:
- Build on each other progressively
- Focus on specific features or integrations
- Are used for testing with every Pipecat release
See the Foundational Examples README for the complete list.
More Advanced Examples
Ready to explore complex use cases? Visit pipecat-examples for:
- Production-ready applications
- Multi-platform client implementations
- Telephony integrations
- Multimodal and creative applications
- Deployment and monitoring examples