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. bosonai logo

    higgs-tts-3-4b

    bosonai·TTS

    ≈6.0 GB

    Higgs TTS 3 is built for voice chat: it speaks, not just reads. It turns model responses into expressive conversational speech across 100+ languages, with zero-shot voice cloning and inline control over emotion, style, prosody, pauses, and sound effects.

    4.7Bboson-higgs-tts-3-research-and-non-commercial-license
    89.5KJun 2026
    • Same category
    • Larger (4.7B vs 28M)
    vs
  2. zai-org logo

    GLM-TTS

    zai-org·TTS

    ? GB

    GLM-TTS is a high-quality text-to-speech (TTS) synthesis system based on large language models, supporting zero-shot voice cloning and streaming inference. The system adopts a two-stage architecture combining an LLM for speech token generation and a Flow Matching model for waveform synthesis.

    ?BMIT
    657Dec 2025
    • Same category
    • Commercial use OK
    vs
  3. OpenMOSS-Team logo

    MOSS-TTS-Local-Transformer

    OpenMOSS-Team·TTS

    ≈4.1 GB

    MOSS‑TTS Family is an open‑source speech and sound generation model family from MOSI.AI and the OpenMOSS team. It is designed for high‑fidelity, high‑expressiveness, and complex real‑world scenarios, covering stable long‑form speech, multi‑speaker dialogue, voice/character design, environmental…

    3.1BApache 2.0
    188.6KFeb 2026gguf
    • Same category
    • Larger (3.1B vs 28M)
    • Commercial use OK
    vs
  4. myshell-ai logo

    MeloTTS-Korean

    myshell-ai·TTS

    ? GB

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

    ?BMIT
    77.3KFeb 2024
    • Same category
    • Commercial use OK
    vs
  5. OpenMOSS-Team logo≈5.9 GB

    MOSS-TTS-Local-Transformer-v1.5 is continued from MOSS-TTS-Local-Transformer-v1.0. 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.

    4.6BApache 2.0
    71.1KJun 2026gguf
    • Same category
    • Larger (4.6B vs 28M)
    • Commercial use OK
    vs
  6. OpenMOSS-Team logo

    MOSS-TTS-v1.5

    OpenMOSS-Team·TTS

    ≈11 GB

    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 2.0
    77.4KMay 2026gguf
    • Same category
    • Larger (8.5B vs 28M)
    • Commercial use OK
    vs
  7. fishaudio logo

    s1-mini

    fishaudio·TTS

    ? GB

    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 4.0
    2.2KMay 2025gguf
    • Same category
    vs
  8. Edge0 logo≈1.8 GB

    This release supports 23 languages, adding 12 languages compared with Preview. It uses the same Transformers inference interface as Preview. This repository includes the complete model checkpoint, its 44.1 kHz neural audio codec, tokenizer, processor, and custom Transformers code.

    601MApache 2.0
    24KOct 2026gguf
    • Same category
    • Larger (601M vs 28M)
    • Commercial use OK
    vs
  9. Edge0 logo≈1.8 GB

    This release supports 23 languages, adding 12 languages compared with Preview. It uses the same Transformers inference interface as Preview. This repository includes the complete model checkpoint, its 44.1 kHz neural audio codec, tokenizer, processor, and custom Transformers code.

    601MApache 2.0
    24KOct 2026gguf
    • Same category
    • Larger (601M vs 28M)
    • Commercial use OK
    vs
  10. BreezeBlue logo

    Breeze-TTS-2

    BreezeBlue·TTS

    ≈4.6 GB

    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-license
    26.7KAug 2026gguf
    • Same category
    • Larger (3.5B vs 28M)
    vs
  11. ByteDance logo

    MegaTTS3

    ByteDance·TTS

    ? GB

    \[!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 2.0
    2.6KMar 2025
    • Same category
    • Commercial use OK
    vs
  12. m-a-p logo

    YuE2-3B

    m-a-p·TTS

    ≈4.8 GB

    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 4.0
    20.6KSept 2026gguf
    • Same category
    • Larger (3.6B vs 28M)
    vs
  13. inclusionAI logo

    Ming-3.0-tts-0.5B

    inclusionAI·TTS

    ≈3.8 GB

    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.

    1.5BMIT
    18.4KSept 2026gguf
    • Same category
    • Larger (1.5B vs 28M)
    • Commercial use OK
    vs
  14. fishaudio logo

    fish-speech-1.5

    fishaudio·TTS

    ? GB

    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 4.0
    5.1KNov 2024
    • Same category
    vs
  15. FunAudioLLM logo

    Fun-CosyVoice3-0.5B-2512

    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
    142.9KDec 2025gguf
    • Same category
    • Larger (500M vs 28M)
    • Commercial use OK
    vs
  16. microsoft logo≈2.8 GB

    VibeVoice-Realtime is a lightweight real‑time text-to-speech model supporting streaming text input and robust long-form speech generation.

    1BMIT
    128.6KDec 2025gguf
    • Same category
    • Larger (1B vs 28M)
    • Commercial use OK
    vs
  17. FunAudioLLM logo

    Fun-CineForge

    FunAudioLLM·TTS

    ? GB

    🎬 Fun-CineForge: A Unified Dataset Pipeline and Model for Zero-Shot Movie Dubbing in Diverse Cinematic Scenes

    ?BApache 2.0
    107Mar 2026
    • Same category
    • Commercial use OK
    vs
  18. microsoft logo

    VibeVoice-1.5B

    microsoft·TTS

    ≈6.5 GB

    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.

    2.7BMIT
    214.7KAug 2025gguf
    • Same category
    • Larger (2.7B vs 28M)
    • Commercial use OK
    vs
  19. myshell-ai logo

    MeloTTS-Chinese

    myshell-ai·TTS

    ? GB

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

    ?BMIT
    25KFeb 2024
    • Same category
    • Commercial use OK
    vs
  20. fishaudio logo

    s2-pro

    fishaudio·TTS

    ≈5.9 GB

    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-license
    42.9KMar 2026gguf
    • Same category
    • Larger (4.6B vs 28M)
    vs
  21. inclusionAI logo

    Ming-3.0-tts-tiny

    inclusionAI·TTS

    ≈11 GB

    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.

    9BA2.5BMIT
    9.5KSept 2026gguf
    • Same category
    • Larger (9B vs 28M)
    • Commercial use OK
    vs
  22. ConwayResearch logo

    Underdog-Woof

    ConwayResearch·TTS

    ? GB

    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-1.0
    10Nov 2026
    • Same category
    vs
  23. 2Noise logo

    ChatTTS

    2Noise·TTS

    ? GB

    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 4.0
    8.2KMay 2024
    • Same category
    vs
  24. SWivid logo

    F5-TTS

    SWivid·TTS

    ≈1.3 GB

    Github: https://github.com/SWivid/F5-TTS Paper: F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching

    336MCC BY-NC 4.0
    1.3MOct 2024gguf
    • Same category
    • Larger (336M vs 28M)
    • Widely used
    vs