Smart Turn
Open-source semantic turn-detection model supporting 23 languages with real-time CPU inference and no GPU required.
Smart Turn scores 4.3/10 (Emerging) in Voice & Realtime.
Language Python License BSD-2-Clause Stars 1.5k★ Type model Self-host Yes Repo pipecat-ai/smart-turn Homepage https://github.com/pipecat-ai/smart-turn
Quality
Emerging 4.3
Adoption 29
Activity 11
Maturity 77
Community 27
Capability 99
Show the math
Overall 4.3/10
value = 4.3/10
score = value
Adoption 3.6/10
value = 29/100
score = 1 + 9 * value / 100
Activity 2/10
value = 11/100
score = 1 + 9 * value / 100
Maturity 7.9/10
value = 76.7/100
score = 1 + 9 * value / 100
Community 3.4/10
value = 27.2/100
score = 1 + 9 * value / 100
Capability 9.9/10
value = 99/100
score = 1 + 9 * value / 100
Key metrics
1.4k★ GitHub stars
0/90d Recent commits
0 devs/90d Recent contributors
99% accuracy Turn-completion accuracy, human English benchmark (Smart Turn v2) Smart Turn v2 model card reports 99% accuracy on the human English turn-detection benchmark (human_5_all). Source: HuggingFace pipecat-ai/smart-turn-v2 (https://huggingface.co/pipecat-ai/smart-turn-v2).
1.3y Project age
5mo ago Last commit
Gotchas
No gotchas documented yet. Contribute one if you know a constraint we missed.
Labels
- Self-hosted
Self-hosted
You deploy and operate it yourself; there is no hosted option here.
turn-detection endpointing semantic multilingual realtime