V

VoiceMem

VoiceMem is an infrastructure providing memory services for voice models, characterized by precision, emotional intelligence, and personality understanding.

🇨🇳 DomesticFreeOpen sourceGeneral开源低延迟双脑架构
Platforms: WebAPI
Region
Domestic
Pricing
Free
Open source
Yes
GitHub Stars
★ 1.0k
Views
1
Source
GitHub
Added
2026-09-09
Last verified
2026-09-09

Overview

VoiceMem is a memory infrastructure designed for next-generation voice agents. It is based on a streaming dual-brain architecture, where the left brain stores information and the right brain manages emotions. Through information compression, hierarchical storage, and streaming queries, VoiceMem achieves low latency. It offers precise, emotionally intelligent, and personality-aware memory services, suitable for personalized interaction scenarios. Users can quickly integrate it into their voice applications with simple installation and configuration.

Key features

  • Streaming dual-brain architecture
  • Low-latency processing
  • Precise and emotionally intelligent memory
  • Plug-and-play components

Use cases

Voice assistantsCustomer service robotsSmart home controlVirtual personal assistants

Pros

  • Low-latency response
  • Precise and emotionally intelligent memory
  • Highly customizable
  • Fully open source

Limitations / notes

  • Requires internet connection
  • Higher learning curve

Who it's for

DevelopersEnterprise teamsResearchers

This overview was compiled by AI from public sources and may contain inaccuracies — please refer to the official site.

FAQ

Is it free?

Yes, VoiceMem is completely open source and free to use.

Do I need scientific internet access?

No, but certain features may rely on external APIs.

Is Chinese support available?

Yes, the project documentation and example code are primarily in Chinese.

Can it be used commercially?

Yes, the project uses an open-source license that allows commercial use.

Similar agents

Something wrong? Let us know on the About page and we'll fix it.