Skip to main content
Deepslate provides official Python SDKs for connecting your voice AI application to the Deepslate Realtime API. All SDKs live in a single open-source monorepo and share a common core, giving you a consistent configuration model and feature set regardless of which agent framework you use.

​
What Deepslate provides

Every SDK gives your application access to Deepslate’s unified voice AI stack over a single WebSocket connection:

Speech-to-Speech Streaming

Send raw PCM audio in, receive synthesized PCM audio out — all in real time

Server-side VAD

Voice Activity Detection runs on the server, so you don’t need a client-side VAD pipeline

LLM Inference

Deepslate manages the inference lifecycle, including tool calling, context management, and interruption handling

ElevenLabs TTS

Optional server-side text-to-speech with configurable voice, model, and regional endpoint

​
Packages

The monorepo publishes three packages. Install only what you need — the framework plugins pull in deepslate-core automatically.

deepslate-livekit

RealtimeModel plugin for LiveKit Agents. Drop into any LiveKit Agents project with a one-line model swap.

deepslate-pipecat

LLMService plugin for Pipecat. Integrates with any Pipecat transport and the full frame-based pipeline architecture.
pip install deepslate-livekit
View source on GitHub: deepslate-livekit · deepslate-pipecat

​
Credentials

All packages read credentials from the same three environment variables: 
DEEPSLATE_VENDOR_ID=your_vendor_id
DEEPSLATE_ORGANIZATION_ID=your_organization_id
DEEPSLATE_API_KEY=your_api_key
Each configuration class (DeepslateOptions, RealtimeModel, etc.) accepts these as constructor arguments too, but environment variables are the recommended approach for keeping secrets out of your code.
Never expose these credentials to clients. All SDK packages are designed for server-side use only.

​
deepslate-core

deepslate-core is the shared foundation that both plugins are built on. It handles WebSocket connectivity, protobuf framing, session lifecycle, and exponential-backoff reconnection.
You don’t need to install deepslate-core directly when using the LiveKit or Pipecat plugins — they include it as a dependency. Install it only if you’re building a custom integration outside of these frameworks.
pip install deepslate-core
The central building block is DeepslateSession, which manages the full protocol lifecycle and delivers events to a DeepslateSessionListener you subclass: 
from deepslate.core import (
    DeepslateOptions,
    DeepslateSession,
    DeepslateSessionListener,
)

class MyListener(DeepslateSessionListener):
    async def on_text_fragment(self, text: str) -> None:
        print(text, end="", flush=True)

    async def on_audio_chunk(
        self, pcm_bytes: bytes, sample_rate: int, channels: int, transcript: str | None
    ) -> None:
        # Forward audio to your output device or transport
        ...

    async def on_tool_call(self, call_id: str, name: str, params: dict) -> None:
        result = await dispatch_tool(name, params)
        await self.session.send_tool_response(call_id, result)

listener = MyListener()
session = DeepslateSession.create(
    DeepslateOptions.from_env(),
    listener=listener,
)
listener.session = session
session.start()
For the full DeepslateSession API — including all send methods and listener callbacks — see the deepslate-core source.

​
Repository

All packages are maintained in a single monorepo managed with uv workspaces: 
deepslate-sdks/
├── packages/
│   ├── core/      # deepslate-core — shared WebSocket client and session logic
│   ├── livekit/   # deepslate-livekit — LiveKit Agents plugin
│   └── pipecat/   # deepslate-pipecat — Pipecat plugin
└── pyproject.toml # uv workspace root
Contributions are welcome. To set up a local development environment: 
git clone https://github.com/deepslate-labs/deepslate-sdks.git
cd deepslate-sdks
uv sync --all-packages

LiveKit Plugin

Full configuration reference, features, and examples

Pipecat Plugin

Full configuration reference, features, and frame reference

GitHub Repository

Source code, issues, and contributions

API Reference

WebSocket message schemas and protocol documentation