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

How to generate spoken replies from recorded input offline with PersonaPlex

Run offline inference on a WAV file to get the model's spoken reply and transcript.

  • Research
  • Advanced
  • 30 minutes
  • From the README
  • Any agent

Who it is forA researcher building an evaluation set for voice agents.

The problemLive sessions are hard to reproduce.

The outcomeRepeatable output.wav and output.json with a fixed seed.

What you need first

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

Steps

  1. Install PersonaPlex and set HF_TOKEN
  2. Prepare an input WAV
  3. Run moshi.offline with --seed for reproducibility
  4. Compare outputs across prompts

Prompt for your agent

Run moshi.offline from NVIDIA/personaplex on <input.wav> with seed 42424242 and two different voice prompts. Report differences between the two outputs.

Caveat. It is research code tied to specific model weights on Hugging Face.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for NVIDIA/personaplex and "Generate spoken replies from recorded input offline"

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