Sopro V2 Turbo: 120M voice cloning TTS runs 5x faster than real time on CPU
Open-source TTS model clones a voice from 5-20s of audio, with ~300ms to first audio on a laptop CPU. Supports English, European Portuguese, French, and German.
1 source
AI Models by email
Get an email when there's news on AI Models
No news that day, no email.
More stories today
- How better grippers can unlock physical AI
- Pentagon adds ChatGPT Mil and Grok for Government to GenAI.mil
- Inkling fine-tuned for speech detail recovery
- Claude Code 2.1.252 fixes Bash, Remote Control bugs
- Vercel AI Gateway adds per-user spending budgets