Pipecat
Open-source framework for real-time voice and multimodal agents.
Composable pipelines that wire speech-to-text, LLMs and text-to-speech (or speech-to-speech models) with transport, turn detection and interruptions.
- Vendor
- Daily
- Category
- Voice & audio
- Pricing
- Open source
- Open source
- Yes
- License
- BSD-2-Clause
- Platforms
- Python, Web, iOS, Android
- Launched
- 2024
- Website
- pipecat.ai
Features
- Pluggable STT/LLM/TTS
- Turn detection
- WebRTC transport
Best for
- Real-time / low latency
- Agents
- Chat & assistants
More voice & audio
- ElevenLabs — ElevenLabs. Lifelike AI voice, dubbing and voice agents.
- Whisper — OpenAI. Open-source multilingual speech recognition.
- Suno — Suno. Make any song you can imagine.
- Deepgram — Deepgram. Speech-to-text and voice AI APIs.
- LiveKit Agents — LiveKit. Framework for real-time voice AI agents.
- AssemblyAI — AssemblyAI. Speech AI models for transcription and understanding.
- Vapi — Vapi. Voice AI agents for developers.
- Cartesia — Cartesia. Ultra-low-latency voice API for real-time agents.