ten-framework
An open-source real-time multimodal conversational AI framework.
- Region
- Overseas
- Pricing
- Free
- Open source
- Yes
- GitHub Stars
- ★ 10.6k
- Source
- GitHub
- Added
- 2026-06-05
- Last verified
- 2026-06-05
Overview
TEN is an open-source real-time multimodal conversational AI framework designed to empower developers with the ability to build low-latency, high-quality voice assistants. It supports RTC and WebSocket connections and can be extended with features such as memory, VAD (Voice Activity Detection), and turn-taking detection. With this framework, users can quickly develop applications like multifunctional voice assistants and interactive whiteboards.
Key features
- ▪Supports real-time multimodal conversation
- ▪Low-latency, high-quality speech processing
- ▪Extensible with various functional modules
- ▪Suitable for diverse application scenarios
Use cases
Pros
- ＋Open source and free to use
- ＋Easy to integrate and extend
- ＋Active community with rich support
Limitations / notes
- －Requires a certain level of technical expertise
Who it's for
This overview was compiled by AI from public sources and may contain inaccuracies — please refer to the official site.
FAQ
How do I get started with the TEN framework?
Visit the official documentation for quick-start guides and example code.
Similar agents
Kimi
FeaturedKimi is a long-context AI assistant by Moonshot AI
豆包
FeaturedAI assistant by ByteDance
DeepSeek
FeaturedDeepSeek is a conversational assistant by DeepSeek
Manus
FeaturedGeneral-purpose autonomous agent capable of autonomously planning and completing complex tasks
ChatGPT Agent
FeaturedA general-purpose agent from OpenAI capable of operating browsers and computers
AutoGPT
One of the earliest autonomous Agents, open-source
Something wrong? Let us know on the About page and we'll fix it.