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 mithi-v1-flash

120 open-weight models that do the same job as mithi-v1-flash (99M 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
Oomni logo

mithi-v1-flash

Oomni·TTS

≈0.7 GB

A small text-to-speech model for 11 Indian languages, with two voices: Satvik (male) and Charvi (female).

99MApache 2.0
1.5KNov 2026
--vram
any
--gpus
--quant
  1. google logo? GB

    Magenta RealTime 2 is offered under a combination of licenses: the codebase is licensed under Apache 2.0, and the model weights under Creative Commons Attribution 4.0 International. In addition, we specify the following usage terms:

    ?BCC BY 4.0
    18.3KMay 2026gguf
    • Same category
    • Commercial use OK
    vs
  2. zeroweight-ai logo

    ZeroTTS

    zeroweight-ai·TTS

    ? GB

    The most accurate open Vietnamese TTS we know of — 4× fewer word errors than the next best model, and it runs faster than real time on a laptop CPU.

    ?BMIT
    8KAug 2026
    • Same category
    • Commercial use OK
    vs
  3. facebook logo

    mms-tts-eng

    facebook·TTS

    ≈0.6 GB

    This repository contains the English (eng) language text-to-speech (TTS) model checkpoint.

    36MCC BY-NC 4.0
    53.7KAug 2023
    • Same category
    • Smaller (36M vs 99M)
    vs
  4. 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
    25.6KOct 2026gguf
    • Same category
    • Larger (601M vs 99M)
    • Commercial use OK
    vs
  5. 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
    25.6KOct 2026gguf
    • Same category
    • Larger (601M vs 99M)
    • Commercial use OK
    vs
  6. 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 99M)
    • Widely used
    vs
  7. 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
    3.8KAug 2026
    • Same category
    vs
  8. nineninesix logo

    gepard-1.0

    nineninesix·TTS

    ≈1.7 GB

    Gepard is a text-to-speech model built for real-time conversation. It starts speaking the moment text begins arriving, generating audio piece by piece instead of waiting for a full sentence — so it feels like a live voice, not a recording.

    556M256K ctx Apache 2.0
    12.7KJun 2026
    • Same category
    • Larger (556M vs 99M)
    • Commercial use OK
    vs
  9. nineninesix logo

    kani-tts-2-en

    nineninesix·TTS

    ≈1.3 GB

    Text-to-Speech Model with Frame-level Position Encodings, optimized for Realtime Conversations

    370M125K ctx lfm1.0
    795Feb 2026
    • Same category
    • Larger (370M vs 99M)
    vs
  10. 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
    965Nov 2026
    • Same category
    • Commercial use OK
    • Newer release
    vs
  11. MBZUAI logo

    LLMVoX

    MBZUAI·TTS

    ≈0.6 GB

    This repository contains the model as described in LLMVoX: Autoregressive Streaming Text-to-Speech Model for Any LLM.

    30MCC BY-NC-SA 4.0
    2.1KMar 2025
    • Same category
    • Smaller (30M vs 99M)
    vs
  12. 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
    1.3KAug 2026gguf
    • Same category
    • Commercial use OK
    vs
  13. facebook logo

    mms-tts-hin

    facebook·TTS

    ≈0.6 GB

    This repository contains the Hindi (hin) language text-to-speech (TTS) model checkpoint.

    36MCC BY-NC 4.0
    8.6KSept 2023
    • Same category
    • Smaller (36M vs 99M)
    vs
  14. 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
    25.9KJun 2025
    • Same category
    vs
  15. nineninesix logo

    kani-tts-2-pt

    nineninesix·TTS

    ≈1.3 GB

    Text-to-Speech Model with Frame-level Position Encodings, optimized for Realtime Conversations

    370M125K ctx lfm1.0
    314Feb 2026gguf
    • Same category
    • Larger (370M vs 99M)
    vs
  16. 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
    15.6KJul 2025gguf
    • Same category
    • Larger (500M vs 99M)
    • Commercial use OK
    vs
  17. 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
    973.2KApr 2026gguf
    • Same category
    • Larger (2.3B vs 99M)
    • Commercial use OK
    vs
  18. 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
    857.9KJan 2026gguf
    • Same category
    • Larger (915M vs 99M)
    • Commercial use OK
    vs
  19. Qwen3-TTS is a series of advanced multilingual, controllable, robust, and streaming text-to-speech models developed by the Qwen team.

    906MApache 2.0
    709.3KJan 2026gguf
    • Same category
    • Larger (906M vs 99M)
    • Commercial use OK
    vs
  20. facebook logo

    mms-tts-ara

    facebook·TTS

    ≈0.6 GB

    This repository contains the Arabic (ara) language text-to-speech (TTS) model checkpoint.

    36MCC BY-NC 4.0
    5.1KSept 2023
    • Same category
    • Smaller (36M vs 99M)
    vs
  21. 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
    648Aug 2026
    • Same category
    • Commercial use OK
    vs
  22. 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 99M)
    • Commercial use OK
    vs
  23. facebook logo

    mms-tts-ind

    facebook·TTS

    ≈0.6 GB

    This repository contains the Indonesian (ind) language text-to-speech (TTS) model checkpoint.

    36MCC BY-NC 4.0
    4.6KSept 2023
    • Same category
    • Smaller (36M vs 99M)
    vs
  24. 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 99M)
    • Commercial use OK
    vs