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.
MOSS-TTS-v1.5 is continued from MOSS-TTS 1.0. It preserves the main 1.0 capabilities, including zero-shot voice cloning, long-form speech generation, token-level duration control, Pinyin/IPA pronunciation control, multilingual synthesis, and code-switching.
8.5BApache 2.076K 223May 2026- Same category
- Larger (8.5B vs 110M)
- Commercial use OK
FishAudio S1 is a leading text-to-speech (TTS) model trained on more than 2 million hours of audio data in multiple languages.
?BCC BY-NC-SA 4.02.2K 809May 2025- Same category
VibeVoice-Realtime is a lightweight real‑time text-to-speech model supporting streaming text input and robust long-form speech generation.
1BMIT122.7K 1.3KDec 2025- Same category
- Larger (1B vs 110M)
- Commercial use OK
Breeze TTS 2 is an open-weight text-to-speech model built for real-time interaction. It ranks #1 among open-weight models on the Artificial Analysis TTS leaderboard, while outperforming frontier proprietary systems.
3.5Bbreezeblue-research-and-non-commercial-license27.1K 1KAug 2026- Same category
- Larger (3.5B vs 110M)
\[!TIP] \[IMPORTANT] For security issues, we do not upload the parameters of WaveVAE encoder to the above links. You can only use the pre-extracted latents from link1 for inference. If you want to synthesize speech for speaker A, you need "A.wav" and "A.npy" in the same directory.
?BApache 2.02.8K 421Mar 2025- Same category
- Commercial use OK
YuE2 is an open music generation model with frontier song quality competitive with Suno v5/v6. Turn lyrics and a style prompt into a complete song with vocals and accompaniment, then shape its melody and chords through an editable score.
3.6B24K ctx CC BY-NC 4.020.2K 1.3KSept 2026- Same category
- Larger (3.6B vs 110M)
This repository contains Ming-3.0-tts-0.5B, the dense Ming-3.0-tts checkpoint built on Qwen2.5-0.5B. The checkpoint includes the backbone, DiT head, audio tokenizer, speaker encoder and text tokenizer.
1.5BMIT18.6K 234Sept 2026- Same category
- Larger (1.5B vs 110M)
- Commercial use OK
Fish Speech V1.5 is a leading text-to-speech (TTS) model trained on more than 1 million hours of audio data in multiple languages.
?BCC BY-NC-SA 4.05.3K 789Nov 2024- Same category
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 2.09.3K 377Nov 2026- Same category
- Smaller (5M vs 110M)
- Commercial use OK
🎬 Fun-CineForge: A Unified Dataset Pipeline and Model for Zero-Shot Movie Dubbing in Diverse Cinematic Scenes
?BApache 2.0114 63Mar 2026- Same category
- Commercial use OK
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 2.011.9K 56Oct 2026- Same category
- Smaller (8M vs 110M)
- Commercial use OK
OuteTTS-0.1-350M is a novel text-to-speech synthesis model that leverages pure language modeling without external adapters or complex architectures, built upon the LLaMa architecture using our Oute3-350M-DEV base model, it demonstrates that high-quality speech synthesis is achievable through a…
362M4K ctx CC BY 4.0111 304Nov 2024- Same category
- Larger (362M vs 110M)
- Commercial use OK
VibeVoice is a novel framework designed for generating expressive, long-form, multi-speaker conversational audio, such as podcasts, from text. It addresses significant challenges in traditional Text-to-Speech (TTS) systems, particularly in scalability, speaker consistency, and natural turn-taking.
2.7BMIT214.9K 2.5KAug 2025- Same category
- Larger (2.7B vs 110M)
- Commercial use OK
Key Improvements: - 🔊 Higher Quality: 44.1kHz sampling rate preserves more high-frequency details for better voice cloning - ⚡ More Efficient: Reduced token rate (6.25Hz) lowers computational cost while maintaining performance - 🎓 Fine-tuning Support: Train personalized voice models with SFT or…
802MApache 2.06K 364Dec 2025- Same category
- Larger (802M vs 110M)
- Commercial use OK
MeloTTS is a high-quality multi-lingual text-to-speech library by MyShell.ai. Supported languages include:
?BMIT25K 108Feb 2024- Same category
- Commercial use OK
Fish Audio S2 Pro is a leading text-to-speech (TTS) model with fine-grained inline control of prosody and emotion. Trained on over 10M+ hours of audio data across 80+ languages, the system combines reinforcement learning alignment with a dual-autoregressive architecture.
4.6Bfish-audio-research-license43K 1.5KMar 2026- Same category
- Larger (4.6B vs 110M)
Sarashina2.2-TTS is a Japanese-centric text-to-speech system built on a large language model, developed by SB Intuitions. It supports Japanese and English, delivering high pronunciation accuracy, naturalness, and stability across diverse speaking styles, with zero-shot voice generation support.
810M8K ctx Unknown licence2.1K 76Apr 2026- Same category
- Larger (810M vs 110M)
This repository contains Ming-3.0-tts-tiny, the Ming-3.0-tts mixture-of-experts checkpoint built on Ling V3. Its Ling V3 backbone has 7.9B total parameters and activates about 1.3B parameters per token.
9BA2.5BMIT9.4K 61Sept 2026- Same category
- Larger (9B vs 110M)
- Commercial use OK
Marvis is a cutting-edge conversational speech model designed to enable real-time streaming text-to-speech synthesis. Built with efficiency and accessibility in mind, Marvis addresses the growing need for high-quality, real-time voice synthesis that can run on consumer devices such as Apple…
569MApache 2.0507 77Aug 2025- Same category
- Larger (569M vs 110M)
- Commercial use OK
Underdog Woof is a small English text-to-speech model with two voices: Juno and Mira. It reads phone numbers, dates, prices and codes the way people say them, and it runs on a laptop CPU with nothing but numpy, from a single 40.6 MB file. Try it in your browser at underdog.ai/woof.
?Bunderdog-non-commercial-1.010 267Nov 2026- Same category
We are also training larger-scale models and need computational power and data support. If you can provide assistance, please contact OPEN-SOURCE@2NOISE.COM. Thank you very much.
?BCC BY-NC 4.07.8K 1.7KMay 2024- Same category
MeloTTS is a high-quality multi-lingual text-to-speech library by MyShell.ai. Supported languages include:
?BMIT13.2K 30Feb 2024- Same category
- Commercial use OK
See also the pre-print research paper, the project page, the GitHub repository, and the evaluation pipeline.
750MCC BY 4.04.9K 19Jul 2025- Same category
- Larger (750M vs 110M)
- Commercial use OK
See also the pre-print research paper, the project page, the Colab example, the GitHub repository, and the repository of voices.
1.6BCC BY 4.0133.4K 385Jun 2025- Same category
- Larger (1.6B vs 110M)
- Commercial use OK