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. canopylabs logo

    orpheus-3b-0.1-ft

    canopylabs·TTS

    ≈5.0 GB

    03/18/2025 – We are releasing our 3B Orpheus TTS model with additional finetunes. Code is available on GitHub: CanopyAI/Orpheus-TTS

    3.8B128K ctx Apache 2.0
    49KMar 2025gguf
    • Same category
    • Larger (3.8B vs 28M)
    • Commercial use OK
    vs
  2. nari-labs logo

    Dia-1.6B-0626

    nari-labs·TTS

    ≈4.1 GB

    Dia is a 1.6B parameter text to speech model created by Nari Labs. It was pushed to the Hub using the PytorchModelHubMixin integration.

    1.6BApache 2.0
    24.4KJun 2025
    • Same category
    • Larger (1.6B vs 28M)
    • Commercial use OK
    vs
  3. rumik-ai logo

    rumik-oss-1

    rumik-ai·TTS

    ≈4.5 GB

    rumik-oss 1 is a 3b multilingual text-to-speech model from rumik ai, trained on fewer than 70,000 hours of speech while performing competitively with existing TTS models. it combines code-switched synthesis, description-conditioned delivery, and inline vocalization control, with 24 khz audio output.

    3.4B8K ctx CC BY-NC 4.0
    897Sept 2026
    • Same category
    • Larger (3.4B vs 28M)
    vs
  4. fishaudio logo

    fish-speech-1.4

    fishaudio·TTS

    ? GB

    Fish Speech V1.4 is a leading text-to-speech (TTS) model trained on 700k hours of audio data in multiple languages.

    ?BCC BY-NC-SA 4.0
    409Sept 2024
    • Same category
    vs
  5. FunAudioLLM logo

    CosyVoice2-0.5B

    FunAudioLLM·TTS

    ≈1.6 GB

    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 2.0
    15.2KJul 2025gguf
    • Same category
    • Larger (500M vs 28M)
    • Commercial use OK
    vs
  6. nari-labs logo

    Dia2-2B

    nari-labs·TTS

    ≈4.8 GB

    Dia2 is a streaming dialogue TTS model created by Nari Labs.

    1.9BApache 2.0
    6.7KNov 2025gguf
    • Same category
    • Larger (1.9B vs 28M)
    • Commercial use OK
    vs
  7. openbmb logo

    VoxCPM1.5

    openbmb·TTS

    ≈2.3 GB

    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 2.0
    6KDec 2025gguf
    • Same category
    • Larger (802M vs 28M)
    • Commercial use OK
    vs
  8. sbintuitions logo

    sarashina2.2-tts

    sbintuitions·TTS

    ≈2.3 GB

    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 licence
    2.3KApr 2026gguf
    • Same category
    • Larger (810M vs 28M)
    vs
  9. ai4bharat logo

    IndicF5

    ai4bharat·TTS

    ≈1.3 GB

    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.

    351MMIT
    41.1KMar 2025
    • Same category
    • Larger (351M vs 28M)
    • Commercial use OK
    vs
  10. maya-research logo

    maya1

    maya-research·TTS

    ≈4.4 GB

    Maya-1 is an open-weight text-to-speech model from Maya Research that combines natural-language voice descriptions with inline expressive controls. It generates speech as discrete audio tokens, which are decoded into a 24 kHz waveform.

    3.3B128K ctx Apache 2.0
    8.1KOct 2025gguf
    • Same category
    • Larger (3.3B vs 28M)
    • Commercial use OK
    vs
  11. neuphonic logo

    neutts-nano

    neuphonic·TTS

    ≈1.0 GB

    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 licence
    978Nov 2025gguf
    • Same category
    • Larger (229M vs 28M)
    vs
  12. sesame logo

    csm-1b

    sesame·TTS

    ≈4.0 GB

    CSM (Conversational Speech Model) is a speech generation model from Sesame that generates RVQ audio codes from text and audio inputs. The model architecture employs a Llama backbone and a smaller audio decoder that produces Mimi audio codes.

    1.6BApache 2.0
    33.4KMar 2025gguf
    • Same category
    • Larger (1.6B vs 28M)
    • Commercial use OK
    vs
  13. CAMB-AI logo

    MARS5-TTS

    CAMB-AI·TTS

    ? GB

    This is the repo for the MARS5 English speech model (TTS) from CAMB.AI.

    ?BAGPL 3.0
    509Jun 2024
    • Same category
    • Commercial use OK
    vs
  14. bosonai logo≈7.3 GB

    We are open-sourcing Higgs TTS 2, a powerful audio foundation model pretrained on over 10 million hours of audio data and a diverse set of text data.

    5.8BCustom licence
    9.4KJul 2025gguf
    • Same category
    • Larger (5.8B vs 28M)
    vs
  15. neuphonic logo

    neutts-nano-german

    neuphonic·TTS

    ≈1.0 GB

    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 licence
    310Feb 2026gguf
    • Same category
    • Larger (229M vs 28M)
    vs
  16. openbmb logo

    VoxCPM-0.5B

    openbmb·TTS

    ≈1.6 GB

    VoxCPM is a novel tokenizer-free Text-to-Speech (TTS) system that redefines realism in speech synthesis. By modeling speech in a continuous space, it overcomes the limitations of discrete tokenization and enables two flagship capabilities: context-aware speech generation and true-to-life zero-shot…

    500MApache 2.0
    5.2KSept 2025gguf
    • Same category
    • Larger (500M vs 28M)
    • Commercial use OK
    vs
  17. llm-jp logo

    kaburi-tts

    llm-jp·TTS

    ? GB

    Ryuichiro Higashinaka, Shinnosuke Takamichi, and Tetsuji Ogawa. "KABURI-TTS: Phoneme-Keyed Activity-conditioned Bi-channel Utterance Rendering for Interaction." In Proceedings of the 2026 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), 2026.

    ?BApache 2.0
    0Jul 2026
    • Same category
    • Commercial use OK
    vs
  18. myshell-ai logo

    MeloTTS-English-v2

    myshell-ai·TTS

    ? GB

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

    ?BMIT
    699Feb 2024
    • Same category
    • Commercial use OK
    vs
  19. mistralai logo

    Voxtral-4B-TTS-2603

    mistralai·TTS

    ≈5.3 GB

    Voxtral TTS is a frontier, open-weights text-to-speech model that’s fast, instantly adaptable, and produces lifelike speech for voice agents. The model is released with BF16 weights and a set of reference voices.

    4BCC BY-NC 4.0
    2.7KNov 2025gguf
    • Same category
    • Larger (4B vs 28M)
    vs
  20. nari-labs logo

    Dia2-1B

    nari-labs·TTS

    ≈2.9 GB

    Dia2 is a streaming dialogue TTS model created by Nari Labs.

    1.1BApache 2.0
    2.3KNov 2025gguf
    • Same category
    • Larger (1.1B vs 28M)
    • Commercial use OK
    vs
  21. Zyphra logo≈4.1 GB

    Zonos-v0.1 is a leading open-weight text-to-speech model trained on more than 200k hours of varied multilingual speech, delivering expressiveness and quality on par with—or even surpassing—top TTS providers.

    1.6BApache 2.0
    19.7KFeb 2025gguf
    • Same category
    • Larger (1.6B vs 28M)
    • Commercial use OK
    vs
  22. fishaudio logo

    fish-speech-1.2

    fishaudio·TTS

    ? GB

    Fish Speech V1.2 is a leading text-to-speech (TTS) model trained on 300k hours of English, Chinese, and Japanese audio data.

    ?BCC BY-NC-SA 4.0
    190Jul 2024
    • Same category
    vs
  23. kyutai logo≈2.2 GB

    See also the pre-print research paper, the project page, the GitHub repository, and the evaluation pipeline.

    750MCC BY 4.0
    4.9KJul 2025
    • Same category
    • Larger (750M vs 28M)
    • Commercial use OK
    vs
  24. ResembleAI logo

    chatterbox-flash

    ResembleAI·TTS

    ? GB

    Chatterbox-Flash is a block-diffusion zero-shot TTS model that extends the Chatterbox-TTS pipeline with a parallel masked decoder while preserving streaming generation.

    ?BMIT
    0May 2026
    • Same category
    • Commercial use OK
    vs