Shravani-Limited/VideoAvatar-UK-Voice-Engine

VideoAvatar.ai: UK Regional Voice Engine (v1)

Developed by Shravani Limited, this model is a state-of-the-art Zero-Shot Voice Cloning engine specifically fine-tuned to master the diverse regional accents of the United Kingdom.

🌟 Capabilities

• Zero-Shot Cloning: Clone any voice perfectly with just 3-10 seconds of reference audio. Master your own identity in seconds.
• UK Regional Mastery: Optimized for high-fidelity output in:
  • Northern: Manchester, Scouse, Geordie.
  • Southern: London (Estuary & MLE).
  • Celtic: Scottish (Fife/Edinburgh), Irish (Dublin/Belfast), Welsh (Cardiff).
• Commercial Ready: 100% trained on ethically sourced, commercially cleared datasets (CC-BY 4.0).

🛠️ Technical Details

• Architecture: F5-TTS (Diffusion-based Transformer).
• Updates: 174,000 steps on 4x NVIDIA A10G GPUs.
• Precision: EMA (Exponential Moving Average) weights for stable, human-quality prosody.

🚀 Usage

This model is designed for use with the F5-TTS inference pipeline.

⚖️ License & Ethics

This model is released under the Apache 2.0 license. Shravani Limited is committed to ethical AI—please ensure you have the rights to any voice you attempt to clone.