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. 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
  2. myshell-ai logo

    MeloTTS-Spanish

    myshell-ai·TTS

    ? GB

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

    ?BMIT
    13.2KFeb 2024
    • Same category
    • Commercial use OK
    vs
  3. kyutai logo

    tts-1.6b-en_fr

    kyutai·TTS

    ≈4.1 GB

    See also the pre-print research paper, the project page, the Colab example, the GitHub repository, and the repository of voices.

    1.6BCC BY 4.0
    133.4KJun 2025gguf
    • Same category
    • Larger (1.6B vs 28M)
    • Commercial use OK
    vs
  4. inclusionAI logo

    Ming-3.0-audio-tiny

    inclusionAI·TTS

    ≈11 GB

    Ming-3.0-audio-tiny is a compact native audio-language model from inclusionAI. It accepts audio together with text instructions and supports speech recognition, spoken question answering, audio understanding, audio reasoning, and optional synthesized-speech responses.

    8.9BA2.1BMIT
    5KSept 2026gguf
    • Same category
    • Larger (8.9B vs 28M)
    • Commercial use OK
    vs
  5. mehdi-hf logo

    pocket-tts-farsi-v2

    mehdi-hf·TTS

    ≈0.7 GB

    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 4.0
    0Sept 2026
    • Same category
    • Larger (110M vs 28M)
    vs
  6. myshell-ai logo

    MeloTTS-Japanese

    myshell-ai·TTS

    ? GB

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

    ?BMIT
    8.5KFeb 2024
    • Same category
    • Commercial use OK
    vs
  7. suno logo

    bark-small

    suno·TTS

    ? GB

    Bark is a transformer-based text-to-audio model created by Suno. Bark can generate highly realistic, multilingual speech as well as other audio - including music, background noise and simple sound effects. The model can also produce nonverbal communications like laughing, sighing and crying.

    ?BMIT
    17.3KJul 2023
    • Same category
    • Commercial use OK
    vs
  8. neuphonic logo

    neutts-2e

    neuphonic·TTS

    ≈1.0 GB

    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 licence
    1.1KJul 2026
    • Same category
    • Larger (236M vs 28M)
    vs
  9. myshell-ai logo

    MeloTTS-French

    myshell-ai·TTS

    ? GB

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

    ?BMIT
    6.4KFeb 2024
    • Same category
    • Commercial use OK
    vs
  10. Zyphra logo

    ZONOS3-Mini-hf

    Zyphra·TTS

    ≈2.8 GB

    ZONOS3-Mini is Zyphra's compact text-to-speech model supporting 43 languages, with about 100 million active parameters per token (800 million total in the backbone).

    1BApache 2.0
    1.9KNov 2026
    • Same category
    • Larger (1B vs 28M)
    • Commercial use OK
    vs
  11. Edge0 logo≈1.8 GB

    Audio8 TTS Preview supports multilingual speech generation and zero-shot voice cloning. This repository contains the complete checkpoint, its 44.1 kHz neural audio codec, tokenizer, processor, and Hugging Face remote code.

    601MApache 2.0
    3.8KJul 2026gguf
    • Same category
    • Larger (601M vs 28M)
    • Commercial use OK
    vs
  12. suno logo

    bark

    suno·TTS

    ? GB

    Bark is a transformer-based text-to-audio model created by Suno. Bark can generate highly realistic, multilingual speech as well as other audio - including music, background noise and simple sound effects. The model can also produce nonverbal communications like laughing, sighing and crying.

    ?BMIT
    12.8KApr 2023
    • Same category
    • Commercial use OK
    vs
  13. coqui logo

    XTTS-v2

    coqui·TTS

    ≈1.5 GB

    ⓍTTS is a Voice generation model that lets you clone voices into different languages by using just a quick 6-second audio clip. There is no need for an excessive amount of training data that spans countless hours.

    467Mcoqui-public-model-license
    4.9MOct 2023gguf
    • Same category
    • Larger (467M vs 28M)
    • Widely used
    vs
  14. inclusionAI logo

    Ming-omni-tts-0.5B

    inclusionAI·TTS

    ≈4.1 GB

    Ming-omni-tts is a high-performance unified audio generation model that achieves precise control over speech attributes and enables single-channel synthesis of speech, environmental sounds, and music.

    1.6BApache 2.0
    11.8KFeb 2026
    • Same category
    • Larger (1.6B vs 28M)
    • Commercial use OK
    vs
  15. OpenMOSS-Team logo

    MOSS-TTS-Realtime

    OpenMOSS-Team·TTS

    ≈5.7 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…

    2.3BApache 2.0
    11.6KFeb 2026gguf
    • Same category
    • Larger (2.3B vs 28M)
    • Commercial use OK
    vs
  16. inclusionAI logo

    Ming-3.0-audio-flash

    inclusionAI·TTS

    ≈153 GB

    Ming-3.0-audio-flash is a native audio-language model from inclusionAI. It accepts audio together with text instructions and supports speech recognition, spoken question answering, audio understanding, audio reasoning, and optional synthesized-speech responses.

    128BA6.3BMIT
    2.6KSept 2026
    • Same category
    • Larger (128B vs 28M)
    • Commercial use OK
    vs
  17. OpenMOSS-Team logo

    MOSS-TTSD-v1.0

    OpenMOSS-Team·TTS

    ≈10 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…

    8.4BApache 2.0
    10.7KFeb 2026
    • Same category
    • Larger (8.4B vs 28M)
    • Commercial use OK
    vs
  18. facebook logo? GB

    SeamlessM4T is a collection of models designed to provide high quality translation, allowing people from different linguistic communities to communicate effortlessly through speech and text.

    ?BCC BY-NC 4.0
    7.4KAug 2023
    • Same category
    vs
  19. IndexTeam logo

    Index-TTS

    IndexTeam·TTS

    ? GB

    IndexTTS is a GPT-style text-to-speech (TTS) model mainly based on XTTS and Tortoise. It is capable of correcting the pronunciation of Chinese characters using pinyin and controlling pauses at any position through punctuation marks.

    ?BApache 2.0
    182Mar 2025
    • Same category
    • Commercial use OK
    vs
  20. OpenMOSS-Team logo

    MOSS-VoiceGenerator

    OpenMOSS-Team·TTS

    ≈5.2 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…

    2.1BApache 2.0
    7.2KFeb 2026gguf
    • Same category
    • Larger (2.1B vs 28M)
    • Commercial use OK
    vs
  21. ResembleAI logo

    chatterbox-nano

    ResembleAI·TTS

    ≈0.8 GB

    Chatterbox is a family of four state-of-the-art, open-source text-to-speech models by Resemble AI.

    110MMIT
    0Apr 2026gguf
    • Same category
    • Larger (110M vs 28M)
    • Commercial use OK
    vs
  22. amphion logo

    MaskGCT

    amphion·TTS

    ? GB

    You can use the following code to generate speech from text and a prompt speech.

    ?BCC BY-NC 4.0
    490Oct 2024
    • Same category
    vs
  23. ai4bharat logo

    indic-parler-tts

    ai4bharat·TTS

    ≈2.6 GB

    Indic Parler-TTS is a multilingual Indic extension of Parler-TTS Mini.

    938MApache 2.0
    183KOct 2024
    • Same category
    • Larger (938M vs 28M)
    • Commercial use OK
    vs
  24. OpenMOSS-Team logo

    MOSS-TTS

    OpenMOSS-Team·TTS

    ≈11 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…

    8.5BApache 2.0
    4.9KFeb 2026
    • Same category
    • Larger (8.5B vs 28M)
    • Commercial use OK
    vs