# pipecat-ai/smart-turn

Repository: https://github.com/pipecat-ai/smart-turn
Canonical: https://ross.abutalabs.com/products/smart-turn
Language: Python
License: BSD-2-Clause
License Family: permissive
Last push: 2026-01-29T12:30:26+00:00

## Health v2 (maintenance only)
Score: 49/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 64, release rhythm 35, longevity 39
- inputs: {"age_days": 546, "days_push": 216, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1538, forks 97 (observed 2026-08-28T04:05:00.179036+00:00)

## What it is
Smart Turn is an open-source, audio-native turn detection model that decides when a voice agent should respond to human speech, using prosody and acoustic cues rather than text transcription. It ships with model weights, datasets, and training scripts, and integrates with lightweight VAD like Silero for fast inference.

## Use cases
- detect when a user has finished speaking in a voice agent
- replace VAD-only endpointing with semantic turn detection
- build a realtime conversational voice AI pipeline
- run turn detection locally on CPU with low latency
- support multilingual voice assistants turn-taking
- train or fine-tune a custom turn detection model

## When to choose
- you are building a voice agent and VAD-based endpointing cuts users off or adds latency
- you need a small, fast, self-hostable turn detection model
- you want a truly open model with open weights, datasets, and training code
- you need multilingual turn detection across many languages

## When to avoid
- you only need simple speech/silence segmentation without semantic endpointing
- you need a fully managed cloud speech service rather than a self-run model
- your stack cannot run Python or ONNX inference

## Facets
- artifact type: library
- maturity: active
- function: speech-recognition, machine-learning, audio-processing, llm-inference
- domain: speech-processing, artificial-intelligence
- platform: python, cross-platform, cli
- tags: turn-detection, voice-agents, vad, endpointing, conversational-ai, realtime-audio, onnx, audio, natural-language-processing

## Member repositories
- pipecat-ai/smart-turn (main) score 49

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:00.179036+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:30:58.127779+00:00, confidence not recorded.
  - readme: https://github.com/pipecat-ai/smart-turn (fetched 2026-08-28T04:05:00.179036+00:00, sha 449872bf775b)
- Data as of 2026-08-30T08:39:29.467469+00:00.