selfhost.directory

The index of self-hostable projects — ranked, categorized and served with live updates.
Own your data and stop giving it to big tech.

n4ze3m logo

tiny-voca

n4ze3m·released 14 Nov 2026

Apache 2.05M≈0.5 GB
Runs on CPU or any GPU≈9 MB of weights
hf download n4ze3m/tiny-voca
Setup ↓

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.

How much VRAM does tiny-voca need?

At FP16 / BF16 tiny-voca needs about 0.5 GB of GPU memory.

--vram
any
--gpus
--quant
QuantisationWeightsTotal
4-bitRecommended default for local use0.0 GB ≈0.5 GB
8-bitLossless in practice, twice the size of Q40.0 GB ≈0.5 GB
FP16 / BF16recommendedFull precision, as released0.0 GB ≈0.5 GB

Estimates for the weights plus runtime overhead; activations vary with resolution and batch size. Pick a GPU above and the fit column checks every row against it.

Can the RTX 4060 run tiny-voca? →

Run tiny-voca locally

Quantised versions and downloads

RepositoryFormatQuantSizeDownloads
ggml-org/tiny-voca-GGUFGGUFF320.0 GB546
prithivMLmods/tiny-voca-GGUFGGUF——462
PatnaikAshish/SobbieTTSONNX——100

About tiny-voca

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. • Code: https://github.com/n4ze3m/tiny-voca • Phonemizer: https://github.com/n4ze3m/dizione • Dataset: https://huggingface.co/datasets/n4ze3m/tiny-voca SHA256: • tiny-voca.pt: ebb22871524c5732520fb1652e6aefcec708a7452e83bdd00adcf6181db5ef70 • onnx/model.onnx: fe6d918791a15b82e37465981d7f27a070e46b46635e5a3482fc8dff87a1ae46

Full model card on Hugging Face →

Alternatives to tiny-voca

All alternatives →
cloud0day3 logo

antalia-mini

cloud0day3·TTS

≈0.5 GB

Türkçe özet. Antalia-2 Mini, tek sesli, küçük bir Türkçe metinden konuşmaya (TTS) modelidir: toplam 7,6 milyon parametre, 48 kHz çıkış, sıradan bir işlemcide gerçek zamandan çok daha hızlı.

8MApache 2.0
11.9KOct 2026
owensong logo

Inflect-Nano-v1

owensong·TTS

≈0.5 GB

Inflect-Nano-v1 is a tiny English text-to-speech model with 4.63M total inference parameters, including its vocoder.

5MApache 2.0
0Jun 2026gguf
canberkkkkkk logo

ema-lightning

canberkkkkkk·TTS

? GB

Tiny, fast and accurate Turkish text to speech. A 5.6M-parameter DiT acoustic model and a 3M-parameter vocoder: 8.6M in total, about 34 MB. Apache 2.0.

?BApache 2.0
91.3KOct 2026
Supertone logo

supertonic-3

Supertone·TTS

? GB

Supertonic is a lightweight text-to-speech system for local inference. It runs with ONNX Runtime entirely on your device, with no cloud call required for synthesis.

?BOpenRAIL
81.6KMay 2026gguf
IndexTeam logo

IndexTTS-2.5

IndexTeam·TTS

? GB

IndexTTS-2.5 is a zero-shot text-to-speech model that clones a voice from a single reference audio clip. It supports Chinese, English, Japanese, Spanish and Arabic, with cross-lingual voice transfer and emotion control disentangled from timbre.

?Bbilibili-model-license
32KAug 2026gguf
google logo? GB

Magenta RealTime 2 is offered under a combination of licenses: the codebase is licensed under Apache 2.0, and the model weights under Creative Commons Attribution 4.0 International. In addition, we specify the following usage terms:

?BCC BY 4.0
18.3KMay 2026gguf

tiny-voca FAQ

How much VRAM does tiny-voca need?
About 0.5 GB at FP16 / BF16.
Can tiny-voca run on the RTX 4060?
Yes. It fits at FP16 / BF16 (about 0.5 GB). It fits comfortably on the Apple M4 (16 GB), Radeon RX 6700 XT, RTX 3060 12GB.
Can I use tiny-voca commercially?
Yes. It is released under Apache 2.0. Permissive: use, modify and sell freely; keep the notice and licence text.

Data from Hugging Face, the model card and public leaderboards. Memory and speed figures are estimates; real numbers depend on the runtime, context length and drivers. Always check the licence yourself before commercial use.