tiny-voca limitations: English-only, two voices, no streaming yet

A review of tiny-voca's documentation highlights its limits: English-only, two fixed voices, no voice cloning, frequent mispronunciation of foreign names, and no streaming. The 4.5M-parameter model is 18MB (21MB ONNX) with 24kHz mono output.

2026-11-17 ~ 2026-11-17 · 2 related posts