/story/46922788 Posted by sammyyyyyyy on Saturday February 07, 2026 @05:38AM from the self-post dept. ( 1 comment | on HN )
A 135M parameter TTS model trained for ~$100 on 1 GPU, running ~20× real-time on a base MacBook M3 CPU.
v1.5 highlights (on CPU):
• 250 ms TTFA streaming latency
• 0.05 RTF (~20× real-time)
• Zero-shot voice cloning
• Smaller, faster, more stable
Still not perfect (OOD voices can be tricky, and there are still some artifacts), but a decent upgrade.