Community-maintained integration. This service is built and maintained by adhiraj4802. Pipecat does not test or officially support it. Please report issues and request changes on the source repository. Learn more about community integrations.
Overview
TurnBlendAnalyzer is a turn analyzer backed by turn-blend.onnx, a single 105 MB model file that contains
Silero VAD v6.2, a student model (a Whisper Base encoder trained to reproduce the end-of-turn scores of
p99lab’s turn-1), p99lab’s
turn-1-mini and a logistic blend of the two end-of-turn scores
with the elapsed silence. It runs locally on the CPU, needs no API key or GPU, and decides from audio alone.
On LiveKit’s eot-bench v1.1 (English, 2,288 turns) version 0.2.0 makes
23.5% false cut-offs at a 300 ms latency budget, against 32.5% for version 0.1.0, which used Smart Turn v3.2
in place of the student. It is behind the best hosted models and weakest on short turns. The blend’s weights
were fitted on held-out audio, not on the benchmark; the
benchmark page has the full
tables, the latency measurements and the limits.
English only, because turn-1-mini is English only. For other languages use
Pipecat’s built-in Smart Turn.
Source Repository
Source code, example bot, and issues for the Turn Blend integration
Benchmarks
eot-bench results and CPU latency measurements
Installation
This is a community-maintained package distributed separately frompipecat-ai:
Prerequisites
- Pipecat 1.0 or later (tested with
pipecat-ai1.16.0) - 16 kHz input audio: set
PipelineParams(audio_in_sample_rate=16000) - 2 or more CPU threads; the analyzer scores less often on machines that cannot keep up in real time
~/.cache/turn-blend.
The plugin code, the student model and the blend are Apache-2.0. The model file also contains the unmodified
weights of Silero VAD (MIT) and turn-1-mini (Apache-2.0), and the student was initialised from OpenAI’s Whisper
Base (MIT) and trained on scores from turn-1 (Apache-2.0); all of those licences apply to it.
Usage
Configuration
Callback with the result of each ended turn: the reason (
commit or
timeout), the silence waited, the detection delay and the three scores. The
same dict is kept in last_result.turn.detector.configure(...), or read from a JSON file and
TURN_BLEND_<SETTING> environment variables with load_settings(). The
README lists them.