TEN-framework/ten-turn-detection

Turn detection for full-duplex dialogue communication

45
/ 100
Emerging

This tool helps create more natural-sounding conversations between humans and AI agents. It takes in spoken or typed user input and accurately determines if the user has finished their thought, is waiting for the AI, or intends to continue speaking. AI conversation designers and developers can use this to improve the flow and responsiveness of AI-driven dialogues.

534 stars.

Use this if you need your AI agent to understand precisely when a user has finished speaking, paused, or explicitly requested the AI to wait, preventing awkward interruptions.

Not ideal if your primary need is basic voice activity detection (VAD) without the nuanced understanding of conversation turn-taking intent.

conversational-ai dialogue-systems voice-assistants customer-service-automation ai-agent-design
No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 15 / 25
Community 14 / 25

How are scores calculated?

Stars

534

Forks

35

Language

Python

License

Last pushed

Dec 26, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/TEN-framework/ten-turn-detection"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.