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.

Compare mithi-v1-flash with the top 3
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. OpenMOSS-Team logo

    MOSS-TTS-Nano-100M

    OpenMOSS-Team·TTS

    ≈0.7 GB

    MOSS-TTS-Nano is an open-source multilingual tiny speech generation model from MOSI.AI and the OpenMOSS team. With only 0.1B parameters, it is designed for realtime speech generation, can run directly on CPU without a GPU, and keeps the deployment stack simple enough for local demos, web serving…

    100M32K ctx Apache 2.0
    122.1KApr 2026gguf
    • Same category
    • Similar size (100M vs 99M)
    • Commercial use OK
    vs
  2. hexgrad logo

    Kokoro-82M

    hexgrad·TTS

    ≈0.7 GB

    Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient.

    82MApache 2.0
    13.3MDec 2024gguf
    • Same category
    • Similar size (82M vs 99M)
    • Commercial use OK
    • Widely used
    vs
  3. zaakirio logo

    kokoro-ru

    zaakirio·TTS

    ≈0.7 GB

    Russian text-to-speech at 82M parameters, running 9.8x faster than realtime on a laptop CPU with no GPU. Three fixed voices from consented studio actors.

    82MOpenRAIL
    72.7KJul 2026
    • Same category
    • Similar size (82M vs 99M)
    vs
  4. KittenML logo

    kitten-tts-2-mini

    KittenML·TTS

    ≈0.7 GB

    82M parameters, 16 languages, 118 voices, 24 kHz. ONNX with int8 weights (82.7 MB; runs on CPU, no PyTorch needed), and the float32 PyTorch weights.

    82MApache 2.0
    8.4KNov 2026
    • Same category
    • Similar size (82M vs 99M)
    • Commercial use OK
    • Newer release
    vs
  5. hexgrad logo

    Kokoro-82M-v1.1-zh

    hexgrad·TTS

    ≈0.7 GB

    Kokoro is an open-weight series of small but powerful TTS models.

    82MApache 2.0
    85.6KFeb 2025gguf
    • Same category
    • Similar size (82M vs 99M)
    • Commercial use OK
    vs
  6. Supertone logo

    supertonic-2

    Supertone·TTS

    ≈0.7 GB

    Supertonic is a lightning-fast, on-device text-to-speech system designed for extreme performance with minimal computational overhead. Powered by ONNX Runtime, it runs entirely on your device—no cloud, no API calls, no privacy concerns.

    66MOpenRAIL
    5.5KJan 2026gguf
    • Same category
    • Similar size (66M vs 99M)
    vs
  7. 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
    4.7KJul 2026
    • Same category
    • Similar size (183M vs 99M)
    • Commercial use OK
    vs
  8. 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
    • Similar size (170M vs 99M)
    vs
  9. Supertone logo

    supertonic

    Supertone·TTS

    ≈0.7 GB

    Supertonic is a lightning-fast, on-device text-to-speech system designed for extreme performance with minimal computational overhead. Powered by ONNX Runtime, it runs entirely on your device—no cloud, no API calls, no privacy concerns.

    66MOpenRAIL
    2KNov 2025
    • Same category
    • Similar size (66M vs 99M)
    vs
  10. 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
    190Dec 2025
    • Same category
    • Similar size (80M vs 99M)
    • Commercial use OK
    vs
  11. mehdi-hf logo

    cilla-lite

    mehdi-hf·TTS

    ≈0.7 GB

    Gated, non-commercial (CC BY-NC 4.0): ask for access on this page. Cilla Lite is the small 6-layer model for CPUs, distilled from Cilla with guidance baked in (one pass per frame). It speaks Persian in the voice of a short audio prompt. Built on Pocket TTS by Kyutai.

    110MCC BY-NC 4.0
    0Nov 2026
    • Same category
    • Similar size (110M vs 99M)
    • Newer release
    vs
  12. 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
    • Similar size (110M vs 99M)
    vs
  13. 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 99M)
    vs
  14. 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
    • Similar size (110M vs 99M)
    • Commercial use OK
    vs
  15. 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 99M)
    • Widely used
    vs
  16. 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
    4.3MMar 2026gguf
    • Same category
    • Larger (613M vs 99M)
    • Widely used
    vs
  17. canberkkkkkk logo

    ema-lightning

    canberkkkkkk·TTS

    ? GB

    Tiny, fast and accurate Turkish text to speech. A 5.6M-parameter DiT acoustic model and a 3M-parameter vocoder: 8.6M in total, about 34 MB. Apache 2.0.

    ?BApache 2.0
    91.3KOct 2026
    • Same category
    • Commercial use OK
    vs
  18. 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
    974Nov 2025gguf
    • Same category
    • Larger (229M vs 99M)
    vs
  19. 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
    283Feb 2026gguf
    • Same category
    • Larger (229M vs 99M)
    vs
  20. 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
    2.7MApr 2025gguf
    • Same category
    • Larger (500M vs 99M)
    • Commercial use OK
    • Widely used
    vs
  21. Supertone logo

    supertonic-3

    Supertone·TTS

    ? GB

    Supertonic is a lightweight text-to-speech system for local inference. It runs with ONNX Runtime entirely on your device, with no cloud call required for synthesis.

    ?BOpenRAIL
    81.6KMay 2026gguf
    • Same category
    vs
  22. IndexTeam logo

    IndexTTS-2.5

    IndexTeam·TTS

    ? GB

    IndexTTS-2.5 is a zero-shot text-to-speech model that clones a voice from a single reference audio clip. It supports Chinese, English, Japanese, Spanish and Arabic, with cross-lingual voice transfer and emotion control disentangled from timbre.

    ?Bbilibili-model-license
    32KAug 2026gguf
    • Same category
    vs
  23. 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
    142.2KDec 2025gguf
    • Same category
    • Larger (500M vs 99M)
    • Commercial use OK
    vs
  24. 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
    41.6KMar 2025
    • Same category
    • Larger (351M vs 99M)
    • Commercial use OK
    vs