selfhost.directory

The index of self-hostable projects — ranked, categorized and served with live updates.
Own your data and stop giving it to big tech.

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.

the original
mehdi-hf logo

cilla-mini

mehdi-hf·TTS

≈0.6 GB

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.

28MCC BY-NC 4.0
0Nov 2026
--vram
any
--gpus
--quant
  1. ekwek logo

    Soprano-80M

    ekwek·TTS

    ≈0.7 GB

    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 2.0
    182Dec 2025
    • Same category
    • Larger (80M vs 28M)
    • Commercial use OK
    vs
  2. TeraSpace logo

    TeraTTSv2

    TeraSpace·TTS

    ? GB

    If TeraTTSv2 is useful to you, consider supporting its development. Thank you for your support!

    ?Bterattsv2-openrail-m-commercial-attribution
    4KAug 2026
    • Same category
    vs
  3. k2-fsa logo

    OmniVoice

    k2-fsa·TTS

    ≈1.9 GB

    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 licence
    4.2MMar 2026gguf
    • Same category
    • Larger (613M vs 28M)
    • Widely used
    vs
  4. n4ze3m logo

    tiny-voca

    n4ze3m·TTS

    ≈0.5 GB

    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 2.0
    6.4KNov 2026
    • Same category
    • Smaller (5M vs 28M)
    • Commercial use OK
    vs
  5. owensong logo

    Inflect-Mini-v3

    owensong·TTS

    ? GB

    A complete voice. A smaller footprint. Six English voices. Local generation. More ways to make speech your own.

    ?BApache 2.0
    805Nov 2026
    • Same category
    • Commercial use OK
    vs
  6. tencent logo

    AuK

    tencent·TTS

    ? GB

    AuK is a 1.5B foundation model for speech generation and editing. Trained on millions of hours of diverse audio data, AuK supports zero-shot and instruction-based TTS, content and acoustic editing, paralinguistic editing, speech enhancement, and source separation through a unified natural-language…

    ?BMIT
    1.4KAug 2026gguf
    • Same category
    • Commercial use OK
    vs
  7. IndexTeam logo

    IndexTTS-2

    IndexTeam·TTS

    ? GB

    IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech

    ?BUnknown licence
    26KJun 2025
    • Same category
    vs
  8. openbmb logo

    VoxCPM2

    openbmb·TTS

    ≈5.6 GB

    VoxCPM2 is a tokenizer-free, diffusion autoregressive Text-to-Speech model — 2B parameters, 30 languages, 48kHz audio output, trained on over 2 million hours of multilingual speech data.

    2.3BApache 2.0
    971.2KApr 2026gguf
    • Same category
    • Larger (2.3B vs 28M)
    • Commercial use OK
    vs
  9. tencent logo

    AuK-Flash

    tencent·TTS

    ? GB

    AuK is a 1.5B foundation model for speech generation and editing. Trained on millions of hours of diverse audio data, AuK supports zero-shot and instruction-based TTS, content and acoustic editing, paralinguistic editing, speech enhancement, and source separation through a unified natural-language…

    ?BMIT
    664Aug 2026
    • Same category
    • Commercial use OK
    vs
  10. SWivid logo

    E2-TTS

    SWivid·TTS

    ? GB

    E2-TTS is an open-weight tts model from SWivid, published on Hugging Face.

    ?BCC BY-NC 4.0
    83.2KOct 2024
    • Same category
    vs
  11. Qwen3-TTS covers 10 major languages (Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, and Italian) as well as multiple dialectal voice profiles to meet global application needs.

    1.9BApache 2.0
    1.1MJan 2026gguf
    • Same category
    • Larger (1.9B vs 28M)
    • Commercial use OK
    vs
  12. Qwen logo≈2.5 GB

    Qwen3-TTS is a family of advanced multilingual, controllable, robust, and streaming text-to-speech models. Trained on over 5 million hours of speech data spanning 10 languages, Qwen3-TTS supports state-of-the-art 3-second voice cloning and description-based control.

    915MApache 2.0
    839.5KJan 2026gguf
    • Same category
    • Larger (915M vs 28M)
    • Commercial use OK
    vs
  13. Qwen3-TTS is a series of advanced multilingual, controllable, robust, and streaming text-to-speech models developed by the Qwen team.

    906MApache 2.0
    715.7KJan 2026gguf
    • Same category
    • Larger (906M vs 28M)
    • Commercial use OK
    vs
  14. Zyphra logo

    ZONOS2

    Zyphra·TTS

    ? GB

    ZONOS2 is our latest text-to-speech model trained on more than 6 million hours of varied multilingual speech, delivering expressiveness and quality on par with—or even surpassing—top TTS providers at low latency with MoE. ZONOS2 excels at high-fidelity and naturalistic voice cloning.

    ?BApache 2.0
    529Jun 2026gguf
    • Same category
    • Commercial use OK
    vs
  15. freyavoice logo

    Freya-TTS

    freyavoice·TTS

    ≈0.9 GB

    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 2.0
    4.5KJul 2026
    • Same category
    • Larger (183M vs 28M)
    • Commercial use OK
    vs
  16. We release Qwen3-TTS, a series of powerful speech generation models developed by Qwen, offering comprehensive support for voice cloning, voice design, ultra-high-quality human-like speech generation, and natural language-based voice control.

    1.9BApache 2.0
    622.4KJan 2026gguf
    • Same category
    • Larger (1.9B vs 28M)
    • Commercial use OK
    vs
  17. owensong logo

    Inflect-Micro-v2

    owensong·TTS

    ? GB

    New: public adaptation toolkit Prepare data, audit train/validation splits, adapt a fixed voice or language, resume training, evaluate checkpoints, and export PyTorch or ONNX packages with the Inflect adaptation toolkit.

    ?BApache 2.0
    373Jun 2026gguf
    • Same category
    • Commercial use OK
    vs
  18. Edge0 logo≈0.9 GB

    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-v1.0
    1.3KAug 2026
    • Same category
    • Larger (170M vs 28M)
    vs
  19. ResembleAI logo

    Dramabox

    ResembleAI·TTS

    ? GB

    Built on LTX-2 by Lightricks. Dramabox is Resemble AI's expressive TTS, trained on top of the LTX-2.3 audio branch under the LTX-2 Community License. Huge thanks to the Lightricks team for open-sourcing the base.

    ?Bltx-2-community
    472Apr 2026
    • Same category
    vs
  20. myshell-ai logo

    MeloTTS-English

    myshell-ai·TTS

    ? GB

    MeloTTS is a high-quality multi-lingual text-to-speech library by MIT and MyShell.ai. Supported languages include:

    ?BMIT
    140KFeb 2024
    • Same category
    • Commercial use OK
    vs
  21. owensong logo

    Inflect-Nano-v2

    owensong·TTS

    ? GB

    New: public adaptation toolkit Prepare data, audit train/validation splits, adapt a fixed voice or language, resume training, evaluate checkpoints, and export PyTorch or ONNX packages with the Inflect adaptation toolkit.

    ?BApache 2.0
    257Jun 2026gguf
    • Same category
    • Commercial use OK
    vs
  22. microsoft logo

    speecht5_tts

    microsoft·TTS

    ? GB

    This model was introduced in SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing by Junyi Ao, Rui Wang, Long Zhou, Chengyi Wang, Shuo Ren, Yu Wu, Shujie Liu, Tom Ko, Qing Li, Yu Zhang, Zhihua Wei, Yao Qian, Jinyu Li, Furu Wei.

    ?BMIT
    279.7KFeb 2023gguf
    • Same category
    • Commercial use OK
    vs
  23. ResembleAI logo

    chatterbox

    ResembleAI·TTS

    ≈1.6 GB

    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.

    500MMIT
    2.6MApr 2025gguf
    • Same category
    • Larger (500M vs 28M)
    • Commercial use OK
    • Widely used
    vs
  24. fishaudio logo

    drama-3

    fishaudio·TTS

    ≈43 GB

    Fish Audio Drama 3 is Fish Audio's new-generation text-to-speech model, built for multi-character scenes and long-form content. It supports multi-speaker generation, voice cloning and natural-language control.

    35.9BA4.7Bfish-audio-research-license
    44.6KOct 2026gguf
    • Same category
    • Larger (35.9B vs 28M)
    vs