Skip to content

LiveKit

Transcribe user audio or hold a live conversation in a LiveKit Agents session with Sprag models.

Overview

Sprag provides an OpenAI compatible API allowing you to run LiveKit Agents on our models out of the box. Set our base URL on LiveKit's OpenAI plugin and invoke one of our models.

Installation

Install LiveKit Agents with the OpenAI extra:

uv add "livekit-agents[openai]"

Then set your Sprag API key as an environment variable:

export SPRAG_API_KEY=<your_sprag_api_key>

You can generate a key from API keys in the Sprag app, or start with the quickstart if you do not have an account yet.

Connection

Pass our base URL and your API key when you construct the service.

ArgumentValue
base_urlhttps://api.sprag.ai/v1
api_keyYour Sprag API key

One base URL covers both REST and realtime.

Services

Speech to text. Transcribe user audio with openai.STT over REST or a realtime websocket.

Realtime LLM. openai.realtime.RealtimeModel replaces separate STT, LLM, and TTS stages with one WebSocket.

Choosing between them

Use speech to text for transcription only, feeding your own LLM and TTS. Use realtime LLM when the agent should listen and speak in one hop, with no separate STT or TTS call.

If you would rather not wire up separate transcription, LLM, and speech stages at all, our realtime API offers a single multimodal model that listens and speaks, with no LiveKit room or agent framework in between.