thomcle / chatterbox-tts

Chatterbox is a state-of-the-art zeroshot TTS (Updated 2 weeks, 5 days ago)

  • Public
  • 701 runs
  • GitHub
  • Weights
  • License
Iterate in playground
Run with an API
Playground API Examples README Versions

Run time and cost

This model costs approximately $0.030 to run on Replicate, or 33 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia T4 GPU hardware. Predictions typically complete within 133 seconds. The predict time for this model varies significantly based on the inputs.

Readme

Chatterbox has been benchmarked against leading closed-source systems like ElevenLabs, and is consistently preferred in side-by-side evaluations.

Whether you’re working on memes, videos, games, or AI agents, Chatterbox brings your content to life. It’s also the first open source TTS model to support emotion exaggeration control, a powerful feature that makes your voices stand out. Try it now on our Hugging Face Gradio app.

Key Details

  • SoTA zeroshot TTS
  • 0.5B Llama backbone
  • Unique exaggeration/intensity control
  • Ultra-stable with alignment-informed inference
  • Trained on 0.5M hours of cleaned data
  • Watermarked outputs
  • Easy voice conversion script
  • Outperforms ElevenLabs

Tips

  • General Use (TTS and Voice Agents):
  • The default settings (exaggeration=0.5, cfg_weight=0.5) work well for most prompts.

  • If the reference speaker has a fast speaking style, lowering cfg_weight to around 0.3 can improve pacing.

  • Expressive or Dramatic Speech:

  • Try lower cfg_weight values (e.g. ~0.3) and increase exaggeration to around 0.7 or higher.
  • Higher exaggeration tends to speed up speech; reducing cfg_weight helps compensate with slower, more deliberate pacing.