AI tools, scored for your job
Get paid to train AI
🤝 You're in the Free & Open Source library — community-built tools you can use without paying. A different concept from our scored AI directory.
Home › Free & Open Source › Gaming › VoiceMem
✦ Free & open sourceGaming

VoiceMem

Universal streaming dual-brain memory infrastructure for real-time voice agents.

VoiceMem: Streaming Dual-Brain Memory for Voice

Universal memory infrastructure separating factual info and emotional attributes for real-time voice agents.

Free forever · open source · Apache-2.0
✓ Needs IT✓ Browser-based✓ Real-time collaboration
7.5
ZEKAI
Essential for voice AI memory.
Free & open source · Gaming
Ease of setup4
Usefulness9
Maintenance9.5
Community7.5
★ 2,643
GITHUB
Sep 2026
UPDATED
Apache-2.0
LICENSE
🛠 Don't want to self-host? We can set it up →
⚡ Quick answer

VoiceMem provides universal long-term memory for voice agents using a streaming dual-brain architecture. It is built for developers creating interactive voice characters or metaverse agents who need low-latency, emotionally aware context.

Runs on
Cross-platform
Hosting
Self-host
Languages
Python
License
Apache-2.0

What it is

It divides memory into a left brain for facts and a right brain for emotional and personality attribution. A fully streaming architecture allows it to prefetch and query memory within a 0-300 ms window before speech completes.

Who it's for

It suits developers building custom voice agents or metaverse NPCs requiring persistent user memory. It does not suit those seeking a drop-in text-only database or projects unwilling to manage speech-to-text and embedding pipelines.

Key features

Streaming Dual-Brain Architecture

Separates fact management in the left brain from emotional and personality tracking in the right brain.

Zero-Latency Pre-Fetching

Performs speculative queries via streaming audio input so memory is ready before the user finishes talking.

Multimodal Input Processing

Processes raw audio directly to capture voiceprints, speaker IDs, scene contexts, and emotional cues.

Low Token Consumption

Injects only Top-K relevant memories into context to minimize LLM token overhead during live sessions.

How to start

Up and running in 3 steps

1
Clone the VoiceMem repository and run pip install voicemem.
2
Download the default model environment using Hugging Face Hub.
3
Initialize the VoiceMem class with your OpenAI API key and start ingesting audio.
Real talk

Our honest verdict

What's great

  • Achieves low latency streaming memory queries during active speech input
  • Stores emotional and relational attributes alongside factual entity data
  • Supports drop-in replacement for all underlying memory and inference components
  • Includes pretrained model families and fine-tuning scripts for custom adapters

Where it falls short

  • Requires an external OpenAI API key for factual extraction and generation tasks
  • Involves managing local speech processing components like ASR, VAD, and voiceprint models
  • Setup demands familiarity with Python environments and pipeline configuration
Cost

Pricing & license

Free under its open-source license, with the only cost coming from running the local inference hardware and optional OpenAI API usage for extraction.

Paid work

Open remote AI-training roles

880 open remote AI-training roles, updated November 15, 2026; most pay $20–$175 an hour. Zekai lists them free; the application goes to the employer’s platform.

See all open roles →
Compare

Alternatives

🎁 Free & open-source alternatives

These reviewed AI tools do the same job instantly — from our scored directory.

Get more

Use it, or have us set it up

📄 Free PDF: VoiceMem for Gaming
A plain-language guide to getting your first result. Sent to your inbox.
🔔 64 people want a full video tutorial — add your vote
🛠 Don't want to set it up yourself?
We'll install, host & configure VoiceMem for you — and train your team.
Get it done for you ↗
Questions

FAQ

How does the dual-brain setup work?

The left brain handles schema and entity-based facts, while the right brain manages long and short-term emotional attribution.

Can I use my own models?

Yes, the architecture is entirely decoupled, allowing you to swap out components including the underlying memory engine.

Radar

Latest AI news

✉️ The weekly free toolkit
The best new free & open-source tools for Gaming — one short email a week, in your language.
Free · 1 email/week · unsubscribe anytime
Get paid to train AI →

See Zekai first in Google