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 tiny-voca

120 open-weight models that do the same job as tiny-voca (5M 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
n4ze3m logo

tiny-voca

n4ze3m·TTS

≈0.5 GB

tiny-voca is a small English text-to-speech model with two voices, F2 (female) and M2 (male). The complete model, including the waveform generator, has 4.5M parameters and was trained from scratch on about 18 hours of synthetic speech. It runs about 70x faster than real time on four CPU threads.

5MApache 2.0
6.4KNov 2026
--vram
any
--gpus
--quant
  1. bosonai logo≈7.3 GB

    We are open-sourcing Higgs TTS 2, a powerful audio foundation model pretrained on over 10 million hours of audio data and a diverse set of text data.

    5.8BCustom licence
    9.4KJul 2025gguf
    • Same category
    • Larger (5.8B vs 5M)
    vs
  2. openbmb logo

    VoxCPM-0.5B

    openbmb·TTS

    ≈1.6 GB

    VoxCPM is a novel tokenizer-free Text-to-Speech (TTS) system that redefines realism in speech synthesis. By modeling speech in a continuous space, it overcomes the limitations of discrete tokenization and enables two flagship capabilities: context-aware speech generation and true-to-life zero-shot…

    500MApache 2.0
    5.2KSept 2025gguf
    • Same category
    • Larger (500M vs 5M)
    • Commercial use OK
    vs
  3. 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
  4. 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
    699Feb 2024
    • Same category
    • Commercial use OK
    vs
  5. 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 5M)
    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 5M)
    • Commercial use OK
    vs
  7. 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
    19.7KFeb 2025gguf
    • Same category
    • Larger (1.6B vs 5M)
    • Commercial use OK
    vs
  8. 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 5M)
    vs
  9. 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
    190Jul 2024
    • Same category
    vs
  10. 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 5M)
    • Commercial use OK
    vs
  11. 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
  12. 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
    250Aug 2026
    • Same category
    • Larger (2.9B vs 5M)
    • Commercial use OK
    vs
  13. 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
    53.3KAug 2023
    • Same category
    • Larger (36M vs 5M)
    vs
  14. 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
    784Feb 2026
    • Same category
    • Larger (370M vs 5M)
    vs
  15. 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
  16. 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
    6.5KApr 2025
    • Same category
    • Larger (9.8B vs 5M)
    • Commercial use OK
    vs
  17. 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
  18. 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 5M)
    • Commercial use OK
    vs
  19. 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
    • Same category
    • Larger (28M vs 5M)
    • Newer release
    vs
  20. 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
    978Nov 2025gguf
    • Same category
    • Larger (229M vs 5M)
    vs
  21. 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
    97Aug 2026
    • Same category
    • Larger (714M vs 5M)
    vs
  22. parler-tts logo≈2.6 GB

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

    938MApache 2.0
    10.6KNov 2024
    • Same category
    • Larger (938M vs 5M)
    • Commercial use OK
    vs
  23. 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
    181Feb 2024
    • Same category
    vs
  24. 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
    29KJun 2024gguf
    • Same category
    • Larger (878M vs 5M)
    • Commercial use OK
    vs