Skip to main content
Community-maintained integration. This service is built and maintained by sprag-ai. Pipecat does not test or officially support it. Please report issues and request changes on the source repository. Learn more about community integrations.

​
Overview

SpragSTTService provides real-time speech-to-text transcription using Sprag’s OpenAI-compatible WebSocket API.

Source Repository

Source code, examples, and issues for the Sprag integration

Sprag Docs

Official Sprag documentation for Pipecat

​
Installation

This is a community-maintained package distributed separately from pipecat-ai.

​
Prerequisites

​
Sprag Account Setup

Before using Sprag STT services, you need:
  1. Sprag Account: Sign up at sprag.ai
  2. API Key: Generate an API key in the Sprag app

​
Required Environment Variables

  • SPRAG_API_KEY: Your Sprag API key. May be passed directly via the api_key constructor argument instead.

​
Configuration

​
str
default:"None"
Sprag API key. Falls back to the SPRAG_API_KEY environment variable.
​
str
default:"wss://api.sprag.ai/v1/audio/transcriptions"
Sprag streaming transcription WebSocket URL.
​
dict | Literal[False] | None
default:"False"
Turn detection mode. False uses the pipeline’s VAD. {"type": "server_vad"} uses Sprag’s server-side VAD.
​
SpragSTTService.Settings
default:"None"
Runtime-configurable settings. The model defaults to "rhythm".
See the source repository for the authoritative, up-to-date list of settings and defaults.

​
Usage

​
Compatibility

Tested with Pipecat v1.12.0 (pipecat-ai>=1.8,<2). Check the source repository for the latest tested version and changelog.