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.
PiVo-1.4M
empero-ai·released 1 Nov 2026
hf download empero-ai/PiVo-1.4MHow 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.
| Quantisation | Total |
|---|---|
| 4-bitRecommended default for local use | ≈0.5 GB |
| 8-bitLossless in practice, twice the size of Q4 | ≈0.5 GB |
| FP16 / BF16recommendedFull precision, as released | ≈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.
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 →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.
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.
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.
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:
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.
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.
Rate this model
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.
0 comments