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

How to give a voice agent a role and a voice with PersonaPlex

Combine a text role prompt with a voice prompt to keep a consistent persona.

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

Voice cloning. Voice conditioning can imitate a voice; only use voices you have rights to.

Who it is forA product team prototyping a customer service voice agent.

The problemVoice agents drift in tone and role.

The outcomeOutput audio and text that follow the given role and voice.

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
  2. Pick a voice prompt such as NATM1.pt
  3. Write a role prompt in a text file
  4. Run moshi.offline with --voice-prompt, --text-prompt and --input-wav

Prompt for your agent

Run PersonaPlex offline with voice prompt <file>, role prompt <text> and input <wav>, then check output.json follows the role.

Caveat. Blackwell GPUs need the extra PyTorch install step from the README.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for NVIDIA/personaplex and "Give a voice agent a role and a voice"

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