πŸŽ™οΈ Audio8-TTS: Free & Fast Zero-Shot Voice Cloning in Google Colab

This repository contains an easy-to-use Google Colab notebook for running Audio8-TTS. Generate realistic speech and perform zero-shot voice cloning using a short reference audio clip.

Runs in Google Colab with a compatible GPU.

πŸŽ₯ Watch the Tutorial: Fastest Voice Clone for FREE | Text to Speech AI by @CoinNoin

πŸš€ Run in Colab: Open Google Colab Notebook

Open In Colab

Get Pro


✨ Features

Multi-Language Support

  • Cantonese
  • Chinese
  • Dutch
  • English
  • French
  • German
  • Italian
  • Japanese
  • Korean
  • Polish
  • Spanish

Two Model Options

  • Audio8-TTS-Preview-0.6B – High Quality
  • Audio8-TTS-Preview-0.1B – Fast/Hybrid

Speech Generation

  • Standard Text-to-Speech
  • Zero-Shot Voice Cloning
  • Reference audio-based voice generation
  • Multilingual speech synthesis

πŸ› οΈ How to Use

  1. Open the Google Colab notebook.
  2. Go to Runtime β†’ Change runtime type.
  3. Select T4 GPU if available.
  4. Run the dependency installation cell.
  5. Select your preferred model (0.6B or 0.1B).
  6. Run the model loading cell.
  7. Enter your target text to generate speech.
  8. For voice cloning, provide the exact transcript of your reference audio.
  9. Upload your reference .wav file.
  10. Generate and download your audio.

🀝 Credits

⚠️ Responsible Use

Only clone voices that you own or have explicit permission to use. Do not use generated voices for impersonation, fraud, or misleading content.

Check the underlying model's license and usage restrictions before commercial use.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support