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 PiVo-1.4M

120 open-weight models that do the same job as PiVo-1.4M (1M 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
empero-ai logo

PiVo-1.4M

empero-ai·TTS

≈0.5 GB

How many parameters does a voice need? PiVo is our attempt at an answer: two English voices, Pi and Vo, from a complete text-to-speech stack with 1,401,562 learned parameters, vocoder included.

1MApache 2.0
0Nov 2026
--vram
any
--gpus
--quant
  1. 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
  2. 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
    700Feb 2024
    • Same category
    • Commercial use OK
    vs
  3. 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 1M)
    vs
  4. 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
    19.8KFeb 2025gguf
    • Same category
    • Larger (1.6B vs 1M)
    • Commercial use OK
    vs
  5. 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
    192Jul 2024
    • Same category
    vs
  6. 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 1M)
    • Commercial use OK
    vs
  7. 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
    2.1KNov 2025
    • Same category
    • Larger (66M vs 1M)
    vs
  8. 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 1M)
    • Commercial use OK
    vs
  9. 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
  10. mispeech logo

    midashenglm-gen

    mispeech·TTS

    ≈7.0 GB

    MiDashengLM-Gen is an end-to-end framework that uses a pre-trained Large Language Model and audio tokenizer as the backbone, combined with per-token conditional flow matching for autoregressive, variable-length mixed-audio scene generation.

    2.9BApache 2.0
    240Aug 2026
    • Same category
    • Larger (2.9B vs 1M)
    • Commercial use OK
    vs
  11. 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
    786Feb 2026
    • Same category
    • Larger (370M vs 1M)
    vs
  12. 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
    696Sept 2023
    • Same category
    vs
  13. moonshotai logo

    Kimi-Audio-7B-Instruct

    moonshotai·TTS

    ≈12 GB

    We present Kimi-Audio, an open-source audio foundation model excelling in audio understanding, generation, and conversation. This repository hosts the model checkpoints for Kimi-Audio-7B-Instruct.

    9.8B8K ctx MIT
    6.4KApr 2025
    • Same category
    • Larger (9.8B vs 1M)
    • Commercial use OK
    vs
  14. FunAudioLLM logo

    PrismAudio

    FunAudioLLM·TTS

    ? GB

    For full training and inference details, please refer to the ThinkSound prismaudio branch.

    ?BMIT
    0Mar 2026
    • Same category
    • Commercial use OK
    vs
  15. nari-labs logo

    Dia-1.6B

    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
    4.9KApr 2025gguf
    • Same category
    • Larger (1.6B vs 1M)
    • Commercial use OK
    vs
  16. 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
    1KNov 2025gguf
    • Same category
    • Larger (229M vs 1M)
    vs
  17. darkps logo

    ice-012-audio

    darkps·TTS

    ≈2.1 GB

    ICE-012 Audio is a multilingual TTS model with streaming output and reference-based voice cloning. It introduces an active acoustic adapter — conditioning codec embeddings before the backbone and refining hidden states after it.

    714MCC BY-NC 4.0
    101Aug 2026
    • Same category
    • Larger (714M vs 1M)
    vs
  18. Here we use the pretained weights from ArTST and fine-tuned using huggingface implementation of SpeechT5 on Classical Arabic ClArTTS for speech synthesis (text-to-speech).

    ?BCC BY-NC 4.0
    172Feb 2024
    • Same category
    vs
  19. parler-tts logo≈2.6 GB

    Parler-TTS Mini Multilingual v1.1 is a multilingual extension of Parler-TTS Mini.

    938MApache 2.0
    9.6KNov 2024
    • Same category
    • Larger (938M vs 1M)
    • Commercial use OK
    vs
  20. 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
    319Feb 2026gguf
    • Same category
    • Larger (229M vs 1M)
    vs
  21. 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
    306Feb 2026gguf
    • Same category
    • Larger (370M vs 1M)
    vs
  22. parler-tts logo

    parler-tts-mini-v1

    parler-tts·TTS

    ≈2.5 GB

    Parler-TTS Mini v1 is a lightweight text-to-speech (TTS) model, trained on 45K hours of audio data, that can generate high-quality, natural sounding speech with features that can be controlled using a simple text prompt (e.g. gender, background noise, speaking rate, pitch and reverberation).

    878MApache 2.0
    26.7KJun 2024gguf
    • Same category
    • Larger (878M vs 1M)
    • Commercial use OK
    vs
  23. inclusionAI logo

    Ming-omni-tts-16.8B-A3B

    inclusionAI·TTS

    ≈22 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.

    17.9BA3BApache 2.0
    290Feb 2026
    • Same category
    • Larger (17.9B vs 1M)
    • Commercial use OK
    vs
  24. coqui logo

    XTTS-v1

    coqui·TTS

    ? GB

    ⓍTTS is a Voice generation model that lets you clone voices into different languages by using just a quick 6-second audio clip. Built on Tortoise, ⓍTTS has important model changes that make cross-language voice cloning and multi-lingual speech generation super easy.

    ?Bcoqui-public-model-license
    224Sept 2023
    • Same category
    vs