Skip to main content

Documentation Index

Fetch the complete documentation index at: https://sambanova-systems.mintlify.dev/docs/llms.txt

Use this file to discover all available pages before exploring further.

PipeCat is an open-source Python framework that handles complex orchestration of AI services, network transport, audio processing, and multimodal interactions. Learn to use the SambaNova LLM and Speech-to-text(STT) integrations and try the example use cases for building real-time speech applications.

​
Prerequisites

  • A SambaCloud account and API key.
  • Ensure Python version 3.11 or 3.12 is installed locally.
  • A PipeCat-compatible STT provider key (e.g., Cartesia).
  • .env file with all your API keys in your working directory.

​
Install dependencies

pip install python-dotenv fastapi uvicorn
pip install pipecat-ai-small-webrtc-prebuilt
pip install pipecat-ai[sambanova, webrtc, silero, daily]

​
Usage

You can integrate SambaNova’s STT and LLM services into your Pipecat pipeline as shown below: 
from pipecat.services.sambanova.llm import SambaNovaLLMService
from pipecat.services.sambanova.stt import SambaNovaSTTService
from pipecat.transcriptions.language import Language
from pipecat.pipeline.pipeline import Pipeline

# Instantiate SambaNova services
sambanova_llm = SambaNovaLLMService(
    api_key='your-sambanova-api-key',
    model='Llama-4-Maverick-17B-128E-Instruct',
    params=SambaNovaLLMService.InputParams(
        temperature=0.7,
        max_tokens=1024
    )
)

sambanova_stt = SambaNovaSTTService(
    model="Whisper-Large-v3",
    api_key="your-sambanova-api-key",
    language=Language.EN,
    prompt="Transcribe the following conversation",
    temperature=0.0
)

# Add the SambaNova models to your pipeline
pipeline = Pipeline([
    transport.input(),
    sambanova_stt,
    ...
    sambanova_llm,
    tts,
    transport.output(),
    ...
])
Follow the integrations example to build and deploy a real-time speech-to-speech weather agent.

​
Additional resources