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

​
Overview

FloeBudgetGuardProcessor is a floe-guard budget processor for Pipecat. Drop one processor after your LLM service and it enforces a spend ceiling one turn at a time — it reserves before a turn, settles on the real usage the pipeline reports, and hard-stops a turn that would cross your budget (so a runaway agent dies at 0.10,notontheinvoice).Itpriceseverylegofthecall—STT(0.10, not on the invoice). It prices every leg of the call — STT (/sec), LLM (/token),TTS(/token), TTS (/1k chars), and telephony ($/min) — from a cost map bundled with the package, so you get a per-call receipt with no account, no API key, and no network calls. Want the hosted counterpart — a unified server-side ledger, enforced spend caps, and per-call cost receipts on a Floe account (BYOK or keyless)? That’s the pipecat-floe services, documented under LLM, STT, and TTS. floe-guard here is the free, local, no-account guardrail; pipecat-floe is its metered, hosted counterpart.

Source Repository

Source code, examples, and issues for floe-guard

PyPI Package

The floe-guard package on PyPI

Runnable demo

A no-network, no-key example that prints a per-leg call receipt

Documentation

floe-guard’s Pipecat setup notes

​
Installation

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

​
Prerequisites

None. floe-guard runs entirely in your process — no account, no API key, no environment variables, and no network calls. Prices come from a cost map that ships with the package.

​
Configuration

FloeBudgetGuardProcessor takes a BudgetGuard (your ceiling) and, optionally, the voice-map vendor for each leg so STT / TTS / telephony are priced automatically: A leg with no vendor and no per-unit override is left un-metered; an unpriceable vendor fails closed rather than metering at a silent $0. Pass a per-unit override for a negotiated rate.

​
Usage

Place the processor directly after the LLM service, and create the PipelineWorker with usage metrics enabled (Pipecat only emits usage frames when they are on):
LLM and TTS auto-meter from the frames Pipecat emits. STT and telephony have no native usage frame, so meter them explicitly (e.g. budget.meter_telephony(1.5) for a 1.5-minute call). A blocked turn pushes a fatal ErrorFrame by default, or invokes your on_budget_exceeded callback. See the runnable example — it runs with no API key and no network and prints a per-leg receipt.

​
Compatibility

Tested with Pipecat 1.x. floe-guard[pipecat] requires pipecat-ai>=1.0.