DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to talk to a full-duplex voice model in your browser with Personaplex

Start the local server and hold a real-time spoken conversation through the web UI.

  • Top pick
  • Research
  • Advanced
  • 1 hour
  • From the README
  • Any agent

Credentials. The HF_TOKEN grants access to your Hugging Face account.

Who it is forA developer evaluating natural, interruptible voice agents.

The problemTurn-based voice bots feel unnatural.

The outcomeA local full-duplex conversation with low latency.

What you need first

  • Linux with an NVIDIA GPU
  • Opus development library
  • A Hugging Face token with access to the model

Steps

  1. Install Opus with sudo apt install libopus-dev
  2. Install with pip install moshi/. and set export HF_TOKEN=
  3. Start with SSL_DIR=$(mktemp -d); python -m moshi.server --ssl "$SSL_DIR"
  4. Open the web UI address the server prints

Prompt for your agent

Install NVIDIA/personaplex, start moshi.server with SSL, and hold a 1 minute conversation. Report latency observations and confirm the server ran on GPU.

Caveat. Add --cpu-offload if the model does not fit in GPU memory.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for NVIDIA/personaplex and "Talk to a full-duplex voice model in your browser"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer