TEN Framework
A source-available framework from Agora and the TEN community for building real-time voice and multimodal conversational agents from reusable extensions.
About TEN Framework
Low-latency voice agents need speech recognition, models, speech synthesis, voice activity detection and turn-taking wired together in real time.
Who it’s for
- Developers building voice assistants and conversational agents
- Teams writing extensions in C++, Go, Python or TypeScript
When to consider it
Consider TEN Framework when you want a modular real-time voice agent stack with its own VAD and turn detection, plus examples for RTC, WebSocket, SIP calls and avatars.
Tradeoffs & limitations
- Licensed under Apache 2.0 with additional conditions (source-available, not OSI open source): it may not be hosted on end-user devices or deployed in ways that compete with Agora. The agent examples need an Agora App ID plus your own model, speech-recognition and speech-synthesis API keys.
SOTA overview · Documentation-based assessment · Sources & review method
Updates
No updates shared yet.
Discussion
Newest firstAsk a question or share how you use TEN Framework.
Keep it helpful. Community rules
Loading discussion…
Sources & review method
Documentation-based assessment · Oct 31, 2026 · Prepared with AI assistance; not a hands-on benchmark.
Checked by SOTA · AI-assisted documentation review. Selection advice is our assessment; verify current requirements for your deployment.
Import history & original evidence
TEN Framework official website
A source-available framework from Agora and the TEN community for building real-time voice and multimodal conversational agents from reusable extensions.
Based on official pages and announcements checked on 2026-10-31. No hands-on test, performance benchmark or popularity ranking is claimed.