MOSS-TTS-Nano is an open-source multilingual tiny speech generation model from MOSI.AI and the OpenMOSS team. With only 0.1B parameters, it is designed for realtime speech generation, can run directly on CPU without a GPU, and keeps the deployment stack simple enough for local demos, web serving…
mithi-v1-flash
Oomni·released 7 Nov 2026
hf download Oomni/mithi-v1-flashA small text-to-speech model for 11 Indian languages, with two voices: Satvik (male) and Charvi (female).
How much VRAM does mithi-v1-flash need?
At FP16 / BF16 mithi-v1-flash needs about 0.7 GB of GPU memory.
| Quantisation | Total |
|---|---|
| 4-bitRecommended default for local use | ≈0.6 GB |
| 8-bitLossless in practice, twice the size of Q4 | ≈0.6 GB |
| FP16 / BF16recommendedFull precision, as released | ≈0.7 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 mithi-v1-flash locally
No runtime support recorded yet. Most models also run through Hugging Face Transformers.
Quantised versions and downloads
| Repository | Format | Quant | Size |
|---|---|---|---|
| chintan992/rustle-tts-mithi-v1-flash | ONNX | — | — |
About mithi-v1-flash
A small text-to-speech model for 11 Indian languages, with two voices: Satvik (male) and Charvi (female). • Languages: Hindi, English, Bengali, Gujarati, Kannada, Malayalam, Marathi, Odia, Punjabi, Tamil, Telugu. • Size: 99.1 M parameters, 197 MB. • Weights: bf16 safetensors. • Output: 24 kHz mono audio. • License: Apache-2.0, free to use, including commercially. See License.
Full model card on Hugging Face →Alternatives to mithi-v1-flash
All alternatives →Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient.
Russian text-to-speech at 82M parameters, running 9.8x faster than realtime on a laptop CPU with no GPU. Three fixed voices from consented studio actors.
82M parameters, 16 languages, 118 voices, 24 kHz. ONNX with int8 weights (82.7 MB; runs on CPU, no PyTorch needed), and the float32 PyTorch weights.
Kokoro is an open-weight series of small but powerful TTS models.
Supertonic is a lightning-fast, on-device text-to-speech system designed for extreme performance with minimal computational overhead. Powered by ONNX Runtime, it runs entirely on your device—no cloud, no API calls, no privacy concerns.
mithi-v1-flash FAQ
- How much VRAM does mithi-v1-flash need?
- About 0.7 GB at FP16 / BF16.
- Can mithi-v1-flash run on the RTX 4060?
- Yes. It fits at FP16 / BF16 (about 0.7 GB). It fits comfortably on the Apple M4 (16 GB), Radeon RX 6700 XT, RTX 3060 12GB.
- Can I use mithi-v1-flash 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