Gated, non-commercial (CC BY-NC 4.0): ask for access on this page. Cilla Lite is the small 6-layer model for CPUs, distilled from Cilla with guidance baked in (one pass per frame). It speaks Persian in the voice of a short audio prompt. Built on Pocket TTS by Kyutai.
Alternatives to cilla-lite
120 open-weight models that do the same job as cilla-lite (110M 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-lite with the top 3MOSS-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
- Similar size (100M vs 110M)
- Commercial use OK
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
- Similar size (82M vs 110M)
- 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
- Similar size (82M vs 110M)
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
- Similar size (99M vs 110M)
- 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
- Similar size (82M vs 110M)
- Commercial use OK
Kokoro is an open-weight series of small but powerful TTS models.
82MApache 2.082.9K 248Feb 2025- Same category
- Similar size (82M vs 110M)
- Commercial use OK
FreyaTTS-small is a 183M-parameter Turkish text-to-speech model, and the open-source member of the FreyaTTS family. It is tokenizer-free at the character level (92 symbols, no phonemizer or G2P) and generates speech with a non-autoregressive conditional flow-matching DiT in the frozen AudioVAE2…
183MApache 2.04.5K 59Jul 2026- Same category
- Similar size (183M vs 110M)
- Commercial use OK
Audio8 TTS 0.1B supports speech generation and zero-shot voice cloning. This repository contains the complete v4 mixed checkpoint, its neural audio codec, tokenizer, processor, and Hugging Face remote code.
170Maudio8-community-license-v1.01.3K 248Aug 2026- Same category
- Similar size (170M vs 110M)
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
- Similar size (66M vs 110M)
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
- Similar size (66M vs 110M)
Soprano is an ultra‑lightweight, on-device text‑to‑speech (TTS) model designed for expressive, high‑fidelity speech synthesis at unprecedented speed.
80M512 ctx Apache 2.0182 314Dec 2025- Same category
- Similar size (80M vs 110M)
- Commercial use OK
A 109.5 M-parameter Persian text-to-speech model with voice cloning from a short audio prompt. Runs on a CPU. Trained on 973 hours of public Persian speech from 2,978 speakers.
110MCC BY-NC 4.00 56Sept 2026- Same category
- Similar size (110M vs 110M)
NeuTTS-2E is a super-fast, highly realistic, on-device emotional TTS speech language model. It is an early alpha release, English-only model, supporting six emotions plus neutral (angry, disgusted, fearful, happy, sad, surprised and neutral) across four fixed speakers (emily, paul, sophie, steven).
236MCustom licence1.1K 46Jul 2026- Same category
- Larger (236M vs 110M)
Github: https://github.com/SWivid/F5-TTS Paper: F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching
336MCC BY-NC 4.01.3M 1.2KOct 2024- Same category
- Larger (336M vs 110M)
- Widely used
Chatterbox is a family of four state-of-the-art, open-source text-to-speech models by Resemble AI.
110MMIT0 50Apr 2026- Same category
- Similar size (110M vs 110M)
- Commercial use OK
OmniVoice is a massively multilingual zero-shot text-to-speech (TTS) model supporting over 600 languages. Built on a novel diffusion language model-style architecture, it delivers high-quality speech with superior inference speed, supporting voice cloning and voice design.
613MUnknown licence4.2M 1.7KMar 2026- Same category
- Larger (613M vs 110M)
- Widely used
State-of-the-art Voice AI has been locked behind web APIs for too long. The NeuTTS Nano Multilingual Collection is a collection of super-fast, highly realistic, on-device TTS speech language models with instant voice cloning - built to run smoothly on CPUs and edge devices.
229MCustom licence978 81Nov 2025- Same category
- Larger (229M vs 110M)
State-of-the-art Voice AI has been locked behind web APIs for too long. The NeuTTS Nano Multilingual Collection is a collection of super-fast, highly realistic, on-device TTS speech language models with instant voice cloning - built to run smoothly on CPUs and edge devices.
229MCustom licence310 27Feb 2026- Same category
- Larger (229M vs 110M)
Chatterbox Multilingual V3 is the latest general-purpose multilingual TTS model in the Chatterbox family. It keeps the same 0.5B model size while improving speaker similarity, reducing hallucinations, and producing more natural, conversational speech across languages.
500MMIT2.6M 1.9KApr 2025- Same category
- Larger (500M vs 110M)
- Commercial use OK
- Widely used
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
Fun-CosyVoice 3.0 is an advanced text-to-speech (TTS) system based on large language models (LLM), surpassing its predecessor (CosyVoice 2.0) in content consistency, speaker similarity, and prosody naturalness. It is designed for zero-shot multilingual speech synthesis in the wild.
500MApache 2.0142.9K 688Dec 2025- Same category
- Larger (500M vs 110M)
- Commercial use OK
We release IndicF5, a near-human polyglot Text-to-Speech (TTS) model trained on 1417 hours of high-quality speech from Rasa, IndicTTS, LIMMITS, and IndicVoices-R.
351MMIT41.1K 479Mar 2025- Same category
- Larger (351M vs 110M)
- 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