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.

empero-ai logo

PiVo-1.4M

empero-ai·released 1 Nov 2026

Apache 2.01M≈0.5 GB
Runs on CPU or any GPU≈3 MB of weights
hf download empero-ai/PiVo-1.4M
Setup ↓

How many parameters does a voice need? PiVo is our attempt at an answer: two English voices, Pi and Vo, from a complete text-to-speech stack with 1,401,562 learned parameters, vocoder included.

How much VRAM does PiVo-1.4M need?

At FP16 / BF16 PiVo-1.4M 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 PiVo-1.4M? →

Run PiVo-1.4M locally

About PiVo-1.4M

How many parameters does a voice need? PiVo is our attempt at an answer: two English voices, Pi and Vo, from a complete text-to-speech stack with 1,401,562 learned parameters, vocoder included. A 584,965-parameter acoustic model predicts vocoder features, and an 816,597-parameter FARGAN-derived vocoder turns them into 16 kHz mono audio. Everything runs locally on a CPU with NumPy and ONNX Runtime. There is no PyTorch, teacher model, speaker encoder or network connection involved at inference time. PiVo is a research model. Its speech is very intelligible, but some sentences still have a metallic or robotic texture. The technical report describes what we measured and what we tried. Author: Leon Lehmann (lehmann@empero.org) · Empero Research (research@empero.org) Both samples read "NASA is ready for the next mission." With Python 3.11 or newer, from a clone of this repository: Or from Python: PiVo uses its own small ONNX runtime, so it does not work with Transformers AutoModel or the hosted Inference API. Our companion code repository adds an installable command-line tool, an HTTP server, a Dockerfile and tests. PiVo speaks English only, in the voices Pi and Vo. Its frontend looks words up in the CMU pronouncing dictionary and expands numbers, currency amounts, ordinals and ISO dates. When a word is not in the dictionary, it raises an error instead of guessing. You can supply the pronunciation in ARPAbet:

Full model card on Hugging Face →

Alternatives to PiVo-1.4M

All alternatives →
n4ze3m logo

tiny-voca

n4ze3m·TTS

≈0.5 GB

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.

5MApache 2.0
7.9KNov 2026
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
82.8KOct 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
82.7KMay 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
31.9KAug 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
18.1KMay 2026gguf
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
12.2KOct 2026

PiVo-1.4M FAQ

How much VRAM does PiVo-1.4M need?
About 0.5 GB at FP16 / BF16.
Can PiVo-1.4M 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 PiVo-1.4M 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.