Overview
BosonRealtimeLLMService connects a Pipecat pipeline to Boson AI’s Higgs
Realtime API. It accepts live audio or text and streams audio or text responses
without requiring separate STT, LLM, and TTS services.
The community integration supports voice activity detection, interruption
handling, user transcriptions, function calling, and text-only responses.
Installation
Install the community-maintained package from PyPI:Configuration
Set your Boson API key and the Higgs Realtime endpoint in the server environment:Common parameters
str
required
Higgs Realtime WebSocket endpoint.
str
required
Boson API key. It is required when using the hosted API.
str
default:"higgs-realtime"
Higgs Realtime model ID.
str
default:"default"
Voice preset or voice ID used for audio responses.
str
System instructions used to initialize the realtime session.
List[Literal['audio', 'text']]
default:"['audio']"
Response modality. Choose exactly one of audio or text.
Dict
default:"server_vad"
OpenAI-compatible server or semantic VAD configuration.
Dict
Optional input transcription configuration. A non-empty model enables user
transcript frames.
Any
Python functions or Pipecat-compatible tool definitions available to the
model.
Minimal pipeline
The following example assumestransport is an existing Pipecat audio
transport:
Compatibility
The current package supportspipecat-ai>=1.4.0,<2 and is tested with Pipecat
v1.6.0. Refer to the integration repository for the latest compatibility
information.
Resources
Integration guide
Setup instructions, complete examples, configuration options, and
troubleshooting
PyPI package
Package releases and installation metadata
Boson documentation
Higgs Realtime API documentation
Boson API keys
Create and configure a Boson API key