Home / Integrations / Pipecat

Score your Pipecat calls.

Drop a 2-channel recorder into your own pipeline. It writes caller and agent to separate channels; Hotato scores the turn-taking timing on the local file. Nothing calls out.

How capture works

A recorder you drop in.

hotato setup --stack pipecat prints a drop-in AudioBufferProcessor(num_channels=2) recorder that writes [caller, agent] as a two-channel WAV inside your pipeline.

Pipecat exposes no recording list for Hotato to pull, so the recorder lives in your process and nothing calls out. Install the live-capture helpers with pip install 'hotato[pipecat]', then score the WAV it wrote.

capture pipelinein your infra
  • AudioBufferProcessornum_channels=2
  • captured.wavcaller + agent
  • capture--stereo
  • scorelocal file
  • scorecard5 dimensions

The scaffold writes caller on channel 0, agent on channel 1, so every overlap keeps its owner all the way to the scorecard.

bashyour infrastructure
Print the drop-in recorder
$ hotato setup --stack pipecat
Score the WAV it wrote
$ hotato capture --stack pipecat --stereo captured.wav
Or score any dual-channel WAV
$ hotato run --stereo captured.wav --expect yield

No pipeline wired yet? hotato capture --stack pipecat --demo runs the loop on a bundled call.

Run it

Setup, record, then score locally.

setup prints the recorder to paste into your pipeline. Point capture at the two-channel WAV it writes, or hand run any dual-channel file you already have.

--expect yield reads a caller who starts talking as an interruption the agent should yield to; --expect hold reads it as a backchannel.

Capture-only

Nothing calls out.

Pipecat capture runs entirely inside your pipeline, and there is no vendor origination API, so Hotato scores what your process writes and never places a call.

Pipecat · what Hotato does
CapabilityPipecatBasis
Capture a recorded callYesA drop-in 2-channel recorder in your pipeline; Hotato scores the local WAV
Drive a live callCapture-onlyNo vendor origination API — Hotato never places Pipecat calls
Credentials & scope

No key to hand over.

Stays in your infraThe recorder runs inside your own process, so no Pipecat credential ever reaches Hotato. When you connect a hosted stack elsewhere, hotato connect stores that key at file mode 0600 and sends it only to that vendor.

ScopeHotato reads turn-taking timingdid_yield, seconds_to_yield, talk_over_sec — from speech energy. No speaker identification, diarization scoring, transcription grading, emotion or intent. Energy is not intent.