Gated, non-commercial (CC BY-NC 4.0): ask for access on this page. Cilla Mini is the 18M model for CPUs, phones and browsers: Cilla shrunk with Kyutai's small-model recipe (8 layers, a 64-dim interface, a one-step drifting sampler head, the 2.6M Mimi decoder), guidance baked in.
Alternatives to cilla-mini
120 open-weight models that do the same job as cilla-mini (28M TTS), ranked by how close they are in task and size, then by popularity and how recent they are. Licence and VRAM are shown for each.
Compare cilla-mini with the top 3This repository contains the model as described in LLMVoX: Autoregressive Streaming Text-to-Speech Model for Any LLM.
30MCC BY-NC-SA 4.01.9K 58Mar 2025- Same category
- Similar size (30M vs 28M)
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.
82MApache 2.013.1M 7.5KDec 2024- Same category
- Larger (82M vs 28M)
- Commercial use OK
- Widely used
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.
82MOpenRAIL72.7K 30Jul 2026- Same category
- Larger (82M vs 28M)
This repository contains the English (eng) language text-to-speech (TTS) model checkpoint.
36MCC BY-NC 4.053.3K 184Aug 2023- Same category
- Similar size (36M vs 28M)
This repository contains the Hindi (hin) language text-to-speech (TTS) model checkpoint.
36MCC BY-NC 4.08.9K 24Sept 2023- Same category
- Similar size (36M vs 28M)
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…
100M32K ctx Apache 2.0122.3K 253Apr 2026- Same category
- Larger (100M vs 28M)
- Commercial use OK
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.
66MOpenRAIL5.4K 398Jan 2026- Same category
- Larger (66M vs 28M)
This repository contains the Arabic (ara) language text-to-speech (TTS) model checkpoint.
36MCC BY-NC 4.04.9K 24Sept 2023- Same category
- Similar size (36M vs 28M)
This repository contains the Indonesian (ind) language text-to-speech (TTS) model checkpoint.
36MCC BY-NC 4.04.3K 25Sept 2023- Same category
- Similar size (36M vs 28M)
This repository contains the Spanish (spa) language text-to-speech (TTS) model checkpoint.
36MCC BY-NC 4.03.7K 26Sept 2023- Same category
- Similar size (36M vs 28M)
This repository contains the Yoruba (yor) language text-to-speech (TTS) model checkpoint.
36MCC BY-NC 4.03.6K 30Sept 2023- Same category
- Similar size (36M vs 28M)
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 2.012K 56Oct 2026- Same category
- Smaller (8M vs 28M)
- Commercial use OK
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.
82MApache 2.01.3K 19Nov 2026- Same category
- Larger (82M vs 28M)
- Commercial use OK
This repository contains the Turkish (tur) language text-to-speech (TTS) model checkpoint.
36MCC BY-NC 4.02.9K 31Sept 2023- Same category
- Similar size (36M vs 28M)
This repository contains the Vietnamese (vie) language text-to-speech (TTS) model checkpoint.
36MCC BY-NC 4.02.9K 38Sept 2023- Same category
- Similar size (36M vs 28M)
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.
66MOpenRAIL2.1K 487Nov 2025- Same category
- Larger (66M vs 28M)
Kokoro is an open-weight series of small but powerful TTS models.
82MApache 2.082.9K 248Feb 2025- Same category
- Larger (82M vs 28M)
- Commercial use OK
This repository contains the Russian (rus) language text-to-speech (TTS) model checkpoint.
36MCC BY-NC 4.01.8K 35Sept 2023- Same category
- Similar size (36M vs 28M)
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 2.079.4K 468Oct 2026- Same category
- Commercial use OK
A small text-to-speech model for 11 Indian languages, with two voices: Satvik (male) and Charvi (female).
99MApache 2.01.4K 83Nov 2026- Same category
- Larger (99M vs 28M)
- Commercial use OK
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.
?BOpenRAIL83.7K 1KMay 2026- Same category
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-license31.8K 277Aug 2026- Same category
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 4.018.3K 267May 2026- Same category
- Commercial use OK
The most accurate open Vietnamese TTS we know of — 4× fewer word errors than the next best model, and it runs faster than real time on a laptop CPU.
?BMIT7.9K 55Aug 2026- Same category
- Commercial use OK