🛠 Tech Stack

💼 About This Role

You'll research and train SOTA TTS models for realistic, emotional voice generation. You'll experiment with architectures and data to improve quality and speed, then deploy to production. You'll collaborate with a team of 3 TTS researchers.

🎯 What You'll Do

• Train and fine-tune SOTA TTS models for voice generation.
• Experiment with different architectures and datasets.
• Deploy optimized TTS models to production.
• Stay current with research and propose improvements.

📋 Requirements

• Experience training text-to-speech or voice cloning models.
• Solid knowledge of transformers, diffusion models, GANs.
• Understanding of speech audio processing (spectrograms, vocoders).
• Proficiency in Python with PyTorch and Hugging Face Transformers.

✨ Nice to Have

• Familiarity with modern speech synthesis models (Vevo, StyleTTS, etc.).
• Contributions to open-source AI or publications in speech processing.
• Familiarity with AWS or similar clusters.