n4ze3m/tiny-voca
text-to-speech · ♥ 395 · ↓ 10.8K
- Tasktext-to-speech
- Downloads6368
- Likes318
- Licenseapache-2.0
text-to-speech · ♥ 395 · ↓ 10.8K
tiny-voca is a small English text-to-speech model with two voices, F2 (female) and M2 (male). The complete model, including the waveform generator, has 4.5M parameters and was trained from scratch on about 18 hours of synthetic speech. It runs about 70x faster than real time on four CPU threads.
Text of any length works. The command reads it one sentence at a time and joins the audio. A text that ends without a mark gets a full stop. A sentence with nothing to read, such as one in another script, is skipped. The saved audio never peaks above 0.99.
Excerpt from the model card on Hugging Face ↗.
n4ze3m/tiny-voca was first seen on Hugging Face · Trending models on Nov 16, 2026. Since then it has appeared in 145 checks on 7 different days. Its best position was #6 of 30, reached on Nov 19, 06:45 UTC. It is #20 right now, slipping from #18 to #20 over the last 6 checks.
Position on Hugging Face · Trending models at every check (lower is better).
Best rank per day (UTC).
🔥 as reported by Hugging Face.
Archived daily, weekly and monthly lists that include this entry.
Yes. As of Nov 22, 16:45 UTC it is #20, slipping from #18 to #20 over the last 6 checks.
#6 on Hugging Face · Trending models, on Nov 19, 06:45 UTC. Trendoday checks this list every 60 minutes.
It was first seen on Nov 16, 2026 and has been on the list on 7 days (145 checks) since.
It is tagged text-to-speech on Hugging Face and has 6368 downloads under the apache-2.0 license.