Apps & Tools
tiny-voca
An ultra-compact 4.5M parameter text-to-speech model that runs 70x faster than real-time
Is this your creation?
PlayableOpen source
Description
A lightweight English TTS model with two voices (M2 and F2) trained from scratch on 18 hours of synthetic speech for under $10. It uses a transformer encoder and source-filter synthesis to achieve high efficiency, ranking in the top 15 on the Open TTS Leaderboard despite its tiny size and CPU-only optimization.
Descriptions, tags, and model credits may be AI-generated or inferred from public sources and can be incomplete or wrong. Learn more.