Lokutor TTS is now a community integration for Pipecat — the leading open-source Python framework for building voice and multimodal conversational AI agents.
What is Pipecat?
Pipecat orchestrates AI services, network transports, and audio processing in a pipeline architecture to enable ultra-low latency conversations. It’s maintained by the Daily.co engineering team and supported by a growing community of developers building real-time voice AI applications.
The Integration
The pipecat-lokutor package provides a LokutorTTSService that plugs directly into any Pipecat pipeline:
from pipecat_lokutor import LokutorTTSService
tts = LokutorTTSService(
api_key="your-key",
sample_rate=44100,
)Install it with a single command:
pip install pipecat-lokutorYou can find the full source code and examples on GitHub: lokutor-ai/pipecat-lokutor.
Why This Matters
Pipecat’s pipeline architecture is a natural fit for Lokutor. Developers building complex voice AI systems can now swap in Lokutor TTS as their speech synthesis backend alongside any STT and LLM combination Pipecat supports.
For the Lokutor community, this means:
- Build sophisticated voice pipelines combining Lokutor TTS with your choice of STT and LLM services
- Leverage Pipecat’s transports for WebRTC, phone (Twilio), and web audio connections
- Access Pipecat’s ecosystem of pre-built components for VAD, interruption handling, and more
Getting Started
Check out the quickstart guide for Pipecat, then add pip install pipecat-lokutor to your dependencies. The package documentation includes a full working example you can run in minutes.
We’re excited to see what the community builds with Lokutor TTS inside Pipecat pipelines. If you build something cool, let us know!