DEDUPED Hot AI repos. Real use cases. What people build. Get the Monday 5

How to run on-device speech on a CPU with Chatterbox-Nano with Chatterbox

Load the 110M Nano model through the Turbo class to generate speech without a GPU.

Short answer: Install with pip install chatterbox-tts; then load ChatterboxTurboTTS.from_pretrained with nano=True and device set to cpu; call model.generate with your text and a reference clip. All steps.

  • Content
  • Beginner
  • 20 minutes
  • From the README
  • Claude Code
  • Codex
  • Cursor
  • Gemini CLI

Who it is forA developer targeting laptops, edge boxes or cheap servers.

The problemMost good TTS models need a GPU.

The outcomeSpeech generated on CPU with the same tag support as Turbo.

What you need first

  • Python 3.11 (developed and tested on Debian 11)
  • A CUDA GPU for Turbo and Multilingual; Nano also runs on CPU
  • A short reference audio clip if you want to clone a voice

Steps

  1. Install with pip install chatterbox-tts
  2. Load ChatterboxTurboTTS.from_pretrained with nano=True and device set to cpu
  3. Call model.generate with your text and a reference clip
  4. Save the WAV and compare speed with Turbo

Prompt for your agent

Using resemble-ai/chatterbox, write a CPU-only script that loads ChatterboxTurboTTS with nano=True and device cpu, generates <my sentence>, and times the run.

Caveat. This card is written from the resemble-ai/chatterbox README, not from a test run by Deduped. Before you start, make sure you have Python 3.11. Check the repo for newer instructions before you rely on these steps.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for resemble-ai/chatterbox and "Run on-device speech on a CPU with Chatterbox-Nano"

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