I Found a Diffusion TTS That Generates Voices from Just a Caption
"Calm adult female narrator voice. Slow, warm, and trustworthy delivery,
carefully reading long sentences."
Enter fullscreen mode
Exit fullscreen mode
Choosing TTS Based on Sound Quality Was Too Slow for Conversations — Separating 'Design' and 'Production' with a Measured 2.5x RTF Difference
I tried to implement a diffusion-based TTS that generates voices from captions for conversational use, but it was 2.5 times slower than a pre-trained model on the same GPU. Even reducing the number of steps didn’t close the gap, so I settled on a two-tier approach: 'Voice design with diffusion, speech with pre-trained models.'
1,195 words~5 min read
